{"data": {"intelligence": [{"model": {"canonical_id": "anthropic/claude-opus-5-5", "name": "Claude Opus 5.5", "organization": {"slug": "anthropic", "name": "Anthropic", "logo_url": "https://platform.claude.com/favicon.ico"}, "family": {"slug": "claude-5-5", "name": "Claude 5 5"}, "url": "/models/anthropic/claude-opus-5-5"}, "intelligence_score": 100.0, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "claude-opus-5-5-max-effort", "raw_score": 85.941291, "score_unit": "percent", "relative_score": 100.0, "weight": 0.5, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "Claude Opus 5.5 (High)", "raw_score": 93.333333, "score_unit": "percent", "relative_score": 100.0, "weight": 0.5, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}], "component_count": 2, "component_coverage": 0.6667, "missing_components": ["lmarena-text"], "coverage_status": "partial", "score_range": {"lower": 66.6667, "upper": 100.0}, "intelligence_rank": 1}, {"model": {"canonical_id": "anthropic/claude-fable-5-1", "name": "Claude Fable 5.1", "organization": {"slug": "anthropic", "name": "Anthropic", "logo_url": "https://platform.claude.com/favicon.ico"}, "family": {"slug": "claude-5-1", "name": "Claude 5 1"}, "url": "/models/anthropic/claude-fable-5-1"}, "intelligence_score": 99.04, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "claude-fable-5-1-max-effort", "raw_score": 86.816836, "score_unit": "percent", "relative_score": 100.0, "weight": 0.333333, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "Claude Fable 5.1 (XHigh)", "raw_score": 90.0, "score_unit": "percent", "relative_score": 97.1201, "weight": 0.333333, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "claude-fable-5.1-max; 95% CI [1503.84123637, 1516.03584930]; votes 14121; rank 3", "raw_score": 1509.938543, "score_unit": "rating", "relative_score": 100.0, "weight": 0.333333, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 3, "component_coverage": 1.0, "missing_components": [], "coverage_status": "complete", "score_range": {"lower": 99.04, "upper": 99.04}, "intelligence_rank": 2}, {"model": {"canonical_id": "openai/gpt-5.5-pro", "name": "GPT-5.5 Pro", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-5-5", "name": "Gpt 5 5"}, "url": "/models/openai/gpt-5-5-pro"}, "intelligence_score": 90.8766, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "GPT-5.5 Pro (High)", "raw_score": 84.58, "score_unit": "percent", "relative_score": 90.8766, "weight": 1.0, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}], "component_count": 1, "component_coverage": 0.3333, "missing_components": ["livebench", "lmarena-text"], "coverage_status": "partial", "score_range": {"lower": 30.2922, "upper": 96.9589}, "intelligence_rank": 3}, {"model": {"canonical_id": "google-deepmind/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "organization": {"slug": "google-deepmind", "name": "Google DeepMind", "logo_url": "https://storage.googleapis.com/gdm-deepmind-com-prod-public/icons/google_deepmind_48dp.svg"}, "family": {"slug": "gemini-3", "name": "Gemini 3"}, "url": "/models/google-deepmind/gemini-3-8-flash"}, "intelligence_score": 89.9786, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "gemini-3.8-flash-high", "raw_score": 80.854991, "score_unit": "percent", "relative_score": 76.6904, "weight": 0.333333, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "Gemini 3.8 Flash (High)", "raw_score": 89.166667, "score_unit": "percent", "relative_score": 96.1602, "weight": 0.333333, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "gemini-3.8-flash-high; 95% CI [1494.01651648, 1503.31692078]; votes 35670; rank 8", "raw_score": 1498.666719, "score_unit": "rating", "relative_score": 97.0853, "weight": 0.333333, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 3, "component_coverage": 1.0, "missing_components": [], "coverage_status": "complete", "score_range": {"lower": 89.9786, "upper": 89.9786}, "intelligence_rank": 4}, {"model": {"canonical_id": "openai/gpt-6.1-sol", "name": "GPT-6.1 Sol", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-6", "name": "Gpt 6"}, "url": "/models/openai/gpt-6.1-sol"}, "intelligence_score": 85.9438, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "gpt-6.1-sol-max", "raw_score": 86.138965, "score_unit": "percent", "relative_score": 100.0, "weight": 0.333333, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "GPT-6.1 Sol (Max)", "raw_score": 94.166667, "score_unit": "percent", "relative_score": 100.0, "weight": 0.333333, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "gpt-6.1-sol-max; 95% CI [1439.17712997, 1455.81824792]; votes 5762; rank 57", "raw_score": 1447.497689, "score_unit": "rating", "relative_score": 57.8313, "weight": 0.333333, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 3, "component_coverage": 1.0, "missing_components": [], "coverage_status": "complete", "score_range": {"lower": 85.9438, "upper": 85.9438}, "intelligence_rank": 5}, {"model": {"canonical_id": "openai/gpt-6-astra", "name": "GPT-6 Astra", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-6", "name": "Gpt 6"}, "url": "/models/openai/gpt-6-astra"}, "intelligence_score": 84.5535, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "gpt-6-astra-max", "raw_score": 86.47107, "score_unit": "percent", "relative_score": 100.0, "weight": 0.333333, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "GPT-6 Astra (Max)", "raw_score": 95.0, "score_unit": "percent", "relative_score": 100.0, "weight": 0.333333, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "gpt-6-astra-max; 95% CI [1435.67981608, 1448.44185822]; votes 11674; rank 72", "raw_score": 1442.060837, "score_unit": "rating", "relative_score": 53.6605, "weight": 0.333333, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 3, "component_coverage": 1.0, "missing_components": [], "coverage_status": "complete", "score_range": {"lower": 84.5535, "upper": 84.5535}, "intelligence_rank": 6}, {"model": {"canonical_id": "qwen/qwen3.8-max", "name": "Qwen3.8-Max", "organization": {"slug": "qwen", "name": "Qwen", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6215ca5692c0ecfba9186921/hrRM50-6XcdWgg2AKpENG.jpeg"}, "family": {"slug": "qwen3-8-max", "name": "Qwen3 8 Max"}, "url": "/models/qwen/qwen3-8-max"}, "intelligence_score": 83.3759, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "qwen3.8-max", "raw_score": 81.879613, "score_unit": "percent", "relative_score": 82.1065, "weight": 0.5, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "qwen3.8-max; 95% CI [1477.45647186, 1487.44466984]; votes 26991; rank 17", "raw_score": 1482.450571, "score_unit": "rating", "relative_score": 84.6452, "weight": 0.5, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 2, "component_coverage": 0.6667, "missing_components": ["arc-agi-2"], "coverage_status": "partial", "score_range": {"lower": 55.5839, "upper": 88.9172}, "intelligence_rank": 7}, {"model": {"canonical_id": "deepseek-ai/DeepSeek-V4.1-Flash", "name": "DeepSeek-V4.1-Flash", "organization": {"slug": "deepseek-ai", "name": "DeepSeek", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6538815d1bdb3c40db94fbfa/xMBly9PUMphrFVMxLX4kq.png"}, "family": {"slug": "deepseek-v4-1", "name": "Deepseek V4 1"}, "url": "/models/deepseek-ai/deepseek-v4-1-flash"}, "intelligence_score": 83.264, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "deepseek-v4.1-flash-max", "raw_score": 83.20017, "score_unit": "percent", "relative_score": 89.0869, "weight": 0.5, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "DeepSeek V4.1 Flash (Max)", "raw_score": 72.916667, "score_unit": "percent", "relative_score": 77.4412, "weight": 0.5, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}], "component_count": 2, "component_coverage": 0.6667, "missing_components": ["lmarena-text"], "coverage_status": "partial", "score_range": {"lower": 55.5093, "upper": 88.8427}, "intelligence_rank": 8}, {"model": {"canonical_id": "google-deepmind/gemini-3.1-pro-preview", "name": "Gemini 3.1 Pro", "organization": {"slug": "google-deepmind", "name": "Google DeepMind", "logo_url": "https://storage.googleapis.com/gdm-deepmind-com-prod-public/icons/google_deepmind_48dp.svg"}, "family": {"slug": "gemini-3", "name": "Gemini 3"}, "url": "/models/google-deepmind/gemini-3-1-pro-preview"}, "intelligence_score": 82.0657, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "gemini-3.1-pro-preview-high", "raw_score": 81.660565, "score_unit": "percent", "relative_score": 80.9486, "weight": 0.333333, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "Gemini 3.1 Pro (Preview)", "raw_score": 77.08, "score_unit": "percent", "relative_score": 82.2371, "weight": 0.333333, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "gemini-3.1-pro-preview; 95% CI [1477.36689416, 1483.27487091]; votes 126781; rank 19", "raw_score": 1480.320883, "score_unit": "rating", "relative_score": 83.0114, "weight": 0.333333, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 3, "component_coverage": 1.0, "missing_components": [], "coverage_status": "complete", "score_range": {"lower": 82.0657, "upper": 82.0657}, "intelligence_rank": 9}, {"model": {"canonical_id": "openai/gpt-5.6-terra", "name": "GPT-5.6 Terra", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-5-6", "name": "Gpt 5 6"}, "url": "/models/openai/gpt-5-6-terra"}, "intelligence_score": 77.2752, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "gpt-5.6-terra-max", "raw_score": 82.314061, "score_unit": "percent", "relative_score": 84.403, "weight": 0.333333, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "GPT-5.6 Terra (Max)", "raw_score": 83.9, "score_unit": "percent", "relative_score": 90.0933, "weight": 0.333333, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "gpt-5.6-terra-xhigh; 95% CI [1442.59739772, 1451.08894108]; votes 42358; rank 59", "raw_score": 1446.843169, "score_unit": "rating", "relative_score": 57.3292, "weight": 0.333333, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 3, "component_coverage": 1.0, "missing_components": [], "coverage_status": "complete", "score_range": {"lower": 77.2752, "upper": 77.2752}, "intelligence_rank": 10}, {"model": {"canonical_id": "xai/grok-4.7", "name": "Grok 4.7", "organization": {"slug": "xai", "name": "xAI", "logo_url": "https://x.ai/favicon.ico"}, "family": {"slug": "grok-4", "name": "Grok 4"}, "url": "/models/xai/grok-4-7"}, "intelligence_score": 73.9898, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "grok-4.7-xhigh", "raw_score": 82.203353, "score_unit": "percent", "relative_score": 83.8178, "weight": 0.5, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "Grok 4.7 (XHigh)", "raw_score": 61.388889, "score_unit": "percent", "relative_score": 64.1618, "weight": 0.5, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}], "component_count": 2, "component_coverage": 0.6667, "missing_components": ["lmarena-text"], "coverage_status": "partial", "score_range": {"lower": 49.3265, "upper": 82.6599}, "intelligence_rank": 11}, {"model": {"canonical_id": "baidu/ernie-5.1", "name": "ERNIE 5.1", "organization": {"slug": "baidu", "name": "Baidu", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/64f187a2cc1c03340ac30498/TYYUxK8xD1AxExFMWqbZD.png"}, "family": {"slug": "ernie-5", "name": "Ernie 5"}, "url": "/models/baidu/ernie-5-1"}, "intelligence_score": 73.4664, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "ernie-5.1; 95% CI [1463.37132109, 1472.38585637]; votes 39489; rank 34", "raw_score": 1467.878589, "score_unit": "rating", "relative_score": 73.4664, "weight": 1.0, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 1, "component_coverage": 0.3333, "missing_components": ["livebench", "arc-agi-2"], "coverage_status": "partial", "score_range": {"lower": 24.4888, "upper": 91.1555}, "intelligence_rank": 12}, {"model": {"canonical_id": "moonshotai/Kimi-K3", "name": "Kimi-K3", "organization": {"slug": "moonshotai", "name": "Moonshot AI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/641c1e77c3983aa9490f8121/X1yT2rsaIbR9cdYGEVu0X.jpeg"}, "family": {"slug": "kimi-k3", "name": "Kimi K3"}, "url": "/models/moonshotai/kimi-k3"}, "intelligence_score": 73.3226, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "kimi-k3", "raw_score": 81.019178, "score_unit": "percent", "relative_score": 77.5583, "weight": 0.333333, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "Kimi K3 (Max)", "raw_score": 60.416667, "score_unit": "percent", "relative_score": 63.0419, "weight": 0.333333, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "kimi-k3-max; 95% CI [1470.96951430, 1480.17280576]; votes 32036; rank 24", "raw_score": 1475.57116, "score_unit": "rating", "relative_score": 79.3677, "weight": 0.333333, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 3, "component_coverage": 1.0, "missing_components": [], "coverage_status": "complete", "score_range": {"lower": 73.3226, "upper": 73.3226}, "intelligence_rank": 13}, {"model": {"canonical_id": "zai-org/glm-5.3", "name": "GLM-5.3", "organization": {"slug": "zai-org", "name": "Z.ai", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/62dc173789b4cf157d36ebee/i_pxzM2ZDo3Ub-BEgIkE9.png"}, "family": {"slug": "glm-5-3", "name": "Glm 5 3"}, "url": "/models/zai-org/glm-5-3"}, "intelligence_score": 71.9085, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "glm-5.3", "raw_score": 79.146315, "score_unit": "percent", "relative_score": 67.6584, "weight": 0.5, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "glm-5.3-max; 95% CI [1466.15226961, 1476.62346864]; votes 21797; rank 27", "raw_score": 1471.387869, "score_unit": "rating", "relative_score": 76.1585, "weight": 0.5, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 2, "component_coverage": 0.6667, "missing_components": ["arc-agi-2"], "coverage_status": "partial", "score_range": {"lower": 47.939, "upper": 81.2723}, "intelligence_rank": 14}, {"model": {"canonical_id": "qwen/qwen3.8-flash", "name": "Qwen3.8-Flash", "organization": {"slug": "qwen", "name": "Qwen", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6215ca5692c0ecfba9186921/hrRM50-6XcdWgg2AKpENG.jpeg"}, "family": {"slug": "qwen3-8-flash", "name": "Qwen3 8 Flash"}, "url": "/models/qwen/qwen3-8-flash"}, "intelligence_score": 67.5206, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "qwen3.8-flash-next", "raw_score": 79.120246, "score_unit": "percent", "relative_score": 67.5206, "weight": 1.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}], "component_count": 1, "component_coverage": 0.3333, "missing_components": ["arc-agi-2", "lmarena-text"], "coverage_status": "partial", "score_range": {"lower": 22.5069, "upper": 89.1735}, "intelligence_rank": 15}, {"model": {"canonical_id": "xai/grok-4.20-multi-agent-0309", "name": "Grok 4.20 Multi-Agent", "organization": {"slug": "xai", "name": "xAI", "logo_url": "https://x.ai/favicon.ico"}, "family": {"slug": "grok-4-20", "name": "Grok 4 20"}, "url": "/models/xai/grok-4-20-multi-agent-0309"}, "intelligence_score": 64.2654, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "Grok 4.20 (Reasoning)", "raw_score": 65.14, "score_unit": "percent", "relative_score": 68.4829, "weight": 0.5, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "grok-4.20-multi-agent-beta-0309; 95% CI [1446.70784633, 1454.06656452]; votes 64959; rank 52", "raw_score": 1450.387205, "score_unit": "rating", "relative_score": 60.048, "weight": 0.5, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 2, "component_coverage": 0.6667, "missing_components": ["livebench"], "coverage_status": "partial", "score_range": {"lower": 42.8436, "upper": 76.177}, "intelligence_rank": 16}, {"model": {"canonical_id": "qwen/qwen3.7-plus", "name": "Qwen3.7-Plus", "organization": {"slug": "qwen", "name": "Qwen", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6215ca5692c0ecfba9186921/hrRM50-6XcdWgg2AKpENG.jpeg"}, "family": {"slug": "qwen3-7-plus", "name": "Qwen3 7 Plus"}, "url": "/models/qwen/qwen3-7-plus"}, "intelligence_score": 63.2905, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "qwen3.7-plus; 95% CI [1450.29323122, 1458.93474328]; votes 42058; rank 46", "raw_score": 1454.613987, "score_unit": "rating", "relative_score": 63.2905, "weight": 1.0, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 1, "component_coverage": 0.3333, "missing_components": ["livebench", "arc-agi-2"], "coverage_status": "partial", "score_range": {"lower": 21.0968, "upper": 87.7635}, "intelligence_rank": 17}, {"model": {"canonical_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "organization": {"slug": "anthropic", "name": "Anthropic", "logo_url": "https://platform.claude.com/favicon.ico"}, "family": {"slug": "claude-5", "name": "Claude 5"}, "url": "/models/anthropic/claude-sonnet-5"}, "intelligence_score": 63.08, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "claude-sonnet-5-xhigh-effort", "raw_score": 80.014756, "score_unit": "percent", "relative_score": 72.249, "weight": 0.5, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "claude-sonnet-5-high; 95% CI [1438.26387267, 1446.51078670]; votes 48998; rank 71", "raw_score": 1442.38733, "score_unit": "rating", "relative_score": 53.9109, "weight": 0.5, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 2, "component_coverage": 0.6667, "missing_components": ["arc-agi-2"], "coverage_status": "partial", "score_range": {"lower": 42.0533, "upper": 75.3866}, "intelligence_rank": 18}, {"model": {"canonical_id": "deepseek-ai/DeepSeek-V4-Pro", "name": "DeepSeek-V4-Pro", "organization": {"slug": "deepseek-ai", "name": "DeepSeek", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6538815d1bdb3c40db94fbfa/xMBly9PUMphrFVMxLX4kq.png"}, "family": {"slug": "deepseek-v4-pro", "name": "Deepseek V4 Pro"}, "url": "/models/deepseek-ai/deepseek-v4-pro"}, "intelligence_score": 57.9366, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "deepseek-v4-pro", "raw_score": 76.786076, "score_unit": "percent", "relative_score": 55.1823, "weight": 0.5, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "deepseek-v4-pro; 95% CI [1447.34331837, 1455.10710237]; votes 57614; rank 49", "raw_score": 1451.22521, "score_unit": "rating", "relative_score": 60.6909, "weight": 0.5, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 2, "component_coverage": 0.6667, "missing_components": ["arc-agi-2"], "coverage_status": "partial", "score_range": {"lower": 38.6244, "upper": 71.9577}, "intelligence_rank": 19}, {"model": {"canonical_id": "zai-org/glm-5.3-flash", "name": "GLM-5.3-Flash", "organization": {"slug": "zai-org", "name": "Z.ai", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/62dc173789b4cf157d36ebee/i_pxzM2ZDo3Ub-BEgIkE9.png"}, "family": {"slug": "glm-5-3-flash", "name": "Glm 5 3 Flash"}, "url": "/models/zai-org/glm-5-3-flash"}, "intelligence_score": 56.2161, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "glm-5.3-flash", "raw_score": 73.270866, "score_unit": "percent", "relative_score": 36.6011, "weight": 0.5, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "glm-5.3-flash; 95% CI [1466.06395213, 1475.85820899]; votes 31379; rank 29", "raw_score": 1470.961081, "score_unit": "rating", "relative_score": 75.8311, "weight": 0.5, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 2, "component_coverage": 0.6667, "missing_components": ["arc-agi-2"], "coverage_status": "partial", "score_range": {"lower": 37.4774, "upper": 70.8108}, "intelligence_rank": 20}, {"model": {"canonical_id": "mistralai/mistral-large-4", "name": "Mistral Large 4", "organization": {"slug": "mistralai", "name": "Mistral AI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/634c17653d11eaedd88b314d/9OgyfKstSZtbmsmuG8MbU.png"}, "family": {"slug": "mistral-large-4", "name": "Mistral Large 4"}, "url": "/models/mistralai/mistral-large-4"}, "intelligence_score": 54.5771, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "mistral-large-4-high", "raw_score": 76.671572, "score_unit": "percent", "relative_score": 54.5771, "weight": 1.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}], "component_count": 1, "component_coverage": 0.3333, "missing_components": ["arc-agi-2", "lmarena-text"], "coverage_status": "partial", "score_range": {"lower": 18.1924, "upper": 84.859}, "intelligence_rank": 21}, {"model": {"canonical_id": "google/gemma-4-31B-it", "name": "Gemma 4 31B", "organization": {"slug": "google-deepmind", "name": "Google DeepMind", "logo_url": "https://storage.googleapis.com/gdm-deepmind-com-prod-public/icons/google_deepmind_48dp.svg"}, "family": {"slug": "gemma-4", "name": "Gemma 4"}, "url": "/models/google-deepmind/gemma-4-31b-it"}, "intelligence_score": 54.2621, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "gemma-4-31b; 95% CI [1435.44854259, 1450.24154456]; votes 6145; rank 67", "raw_score": 1442.845044, "score_unit": "rating", "relative_score": 54.2621, "weight": 1.0, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 1, "component_coverage": 0.3333, "missing_components": ["livebench", "arc-agi-2"], "coverage_status": "partial", "score_range": {"lower": 18.0874, "upper": 84.754}, "intelligence_rank": 22}, {"model": {"canonical_id": "Qwen/Qwen3.8-27B", "name": "Qwen3.8-27B", "organization": {"slug": "qwen", "name": "Qwen", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6215ca5692c0ecfba9186921/hrRM50-6XcdWgg2AKpENG.jpeg"}, "family": {"slug": "qwen3-8-27b", "name": "Qwen3 8 27b"}, "url": "/models/qwen/qwen3-8-27b"}, "intelligence_score": 52.1606, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "qwen3.8-27b", "raw_score": 78.024105, "score_unit": "percent", "relative_score": 61.7265, "weight": 0.333333, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "Qwen3.8-27B (XHigh)", "raw_score": 42.361111, "score_unit": "percent", "relative_score": 42.243, "weight": 0.333333, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "qwen3.8-27b; 95% CI [1435.44919577, 1445.67962049]; votes 22539; rank 74", "raw_score": 1440.564408, "score_unit": "rating", "relative_score": 52.5125, "weight": 0.333333, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 3, "component_coverage": 1.0, "missing_components": [], "coverage_status": "complete", "score_range": {"lower": 52.1606, "upper": 52.1606}, "intelligence_rank": 23}, {"model": {"canonical_id": "Qwen/Qwen3.5-397B-A17B", "name": "Qwen3.5-397B-A17B", "organization": {"slug": "qwen", "name": "Qwen", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6215ca5692c0ecfba9186921/hrRM50-6XcdWgg2AKpENG.jpeg"}, "family": {"slug": "qwen3-5-397b-a17b", "name": "Qwen3 5 397b A17b"}, "url": "/models/qwen/qwen3-5-397b-a17b"}, "intelligence_score": 50.4973, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "qwen3.5-397b-a17b; 95% CI [1434.86253041, 1441.01254684]; votes 92885; rank 80", "raw_score": 1437.937539, "score_unit": "rating", "relative_score": 50.4973, "weight": 1.0, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 1, "component_coverage": 0.3333, "missing_components": ["livebench", "arc-agi-2"], "coverage_status": "partial", "score_range": {"lower": 16.8324, "upper": 83.4991}, "intelligence_rank": 24}, {"model": {"canonical_id": "tencent/Hy3", "name": "Hy3", "organization": {"slug": "tencent", "name": "Tencent", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/5dd96eb166059660ed1ee413/Lp3m-XLpjQGwBItlvn69q.png"}, "family": {"slug": "hy3", "name": "Hy3"}, "url": "/models/tencent/hy3"}, "intelligence_score": 50.1079, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "hy3; 95% CI [1431.24613935, 1443.61359159]; votes 11952; rank 82", "raw_score": 1437.429865, "score_unit": "rating", "relative_score": 50.1079, "weight": 1.0, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 1, "component_coverage": 0.3333, "missing_components": ["livebench", "arc-agi-2"], "coverage_status": "partial", "score_range": {"lower": 16.7026, "upper": 83.3693}, "intelligence_rank": 25}, {"model": {"canonical_id": "google/gemma-4-26B-A4B-it", "name": "Gemma 4 26B-A4B", "organization": {"slug": "google-deepmind", "name": "Google DeepMind", "logo_url": "https://storage.googleapis.com/gdm-deepmind-com-prod-public/icons/google_deepmind_48dp.svg"}, "family": {"slug": "gemma-4", "name": "Gemma 4"}, "url": "/models/google-deepmind/gemma-4-26b-a4b-it"}, "intelligence_score": 47.4086, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "gemma-4-26b-a4b; 95% CI [1426.49659179, 1441.32588678]; votes 6097; rank 90", "raw_score": 1433.911239, "score_unit": "rating", "relative_score": 47.4086, "weight": 1.0, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 1, "component_coverage": 0.3333, "missing_components": ["livebench", "arc-agi-2"], "coverage_status": "partial", "score_range": {"lower": 15.8029, "upper": 82.4695}, "intelligence_rank": 26}, {"model": {"canonical_id": "thinkingmachines/Inkling", "name": "Inkling", "organization": {"slug": "thinkingmachines", "name": "Thinking Machines Lab", "logo_url": "https://thinkingmachines.ai/images/apple-touch-icon.png"}, "family": {"slug": "inkling", "name": "Inkling"}, "url": "/models/thinkingmachines/inkling"}, "intelligence_score": 47.3527, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "inkling-xhigh", "raw_score": 76.470779, "score_unit": "percent", "relative_score": 53.5157, "weight": 0.333333, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "Inkling", "raw_score": 36.527778, "score_unit": "percent", "relative_score": 35.5233, "weight": 0.333333, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "inkling; 95% CI [1436.89849760, 1445.55102061]; votes 39763; rank 73", "raw_score": 1441.224759, "score_unit": "rating", "relative_score": 53.0191, "weight": 0.333333, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 3, "component_coverage": 1.0, "missing_components": [], "coverage_status": "complete", "score_range": {"lower": 47.3527, "upper": 47.3527}, "intelligence_rank": 27}, {"model": {"canonical_id": "mistralai/mistral-large-2512", "name": "Mistral Large 3", "organization": {"slug": "mistralai", "name": "Mistral AI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/634c17653d11eaedd88b314d/9OgyfKstSZtbmsmuG8MbU.png"}, "family": {"slug": "mistral-large-3", "name": "Mistral Large 3"}, "url": "/models/mistralai/mistral-large-2512"}, "intelligence_score": 42.9511, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "mistral-large-3; 95% CI [1425.26985271, 1430.93177803]; votes 83498; rank 99", "raw_score": 1428.100815, "score_unit": "rating", "relative_score": 42.9511, "weight": 1.0, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 1, "component_coverage": 0.3333, "missing_components": ["livebench", "arc-agi-2"], "coverage_status": "partial", "score_range": {"lower": 14.317, "upper": 80.9837}, "intelligence_rank": 28}, {"model": {"canonical_id": "openai/gpt-6-luna", "name": "GPT-6 Luna", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-6", "name": "Gpt 6"}, "url": "/models/openai/gpt-6-luna"}, "intelligence_score": 42.2682, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "gpt-6-luna-max", "raw_score": 75.837013, "score_unit": "percent", "relative_score": 50.1657, "weight": 0.333333, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "GPT-6 Luna (Max)", "raw_score": 59.305556, "score_unit": "percent", "relative_score": 61.762, "weight": 0.333333, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "gpt-6-luna-max; 95% CI [1386.83332056, 1396.17715895]; votes 43294; rank 165", "raw_score": 1391.50524, "score_unit": "rating", "relative_score": 14.8771, "weight": 0.333333, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 3, "component_coverage": 1.0, "missing_components": [], "coverage_status": "complete", "score_range": {"lower": 42.2682, "upper": 42.2682}, "intelligence_rank": 29}, {"model": {"canonical_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", "name": "NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", "organization": {"slug": "nvidia", "name": "NVIDIA", "logo_url": "https://www.nvidia.com/etc/designs/nvidiaGDC/clientlibs_base/images/NVIDIA-Logo.svg"}, "family": {"slug": "nvidia-nemotron-3-ultra-550b-a55b-bf16", "name": "Nvidia Nemotron 3 Ultra 550b A55b Bf16"}, "url": "/models/nvidia/nvidia-nemotron-3-ultra-550b-a55b-bf16"}, "intelligence_score": 37.77, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "nemotron-3-ultra-550b-a55b", "raw_score": 73.491995, "score_unit": "percent", "relative_score": 37.77, "weight": 1.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}], "component_count": 1, "component_coverage": 0.3333, "missing_components": ["arc-agi-2", "lmarena-text"], "coverage_status": "partial", "score_range": {"lower": 12.59, "upper": 79.2567}, "intelligence_rank": 30}, {"model": {"canonical_id": "thinkingmachines/Inkling-Small", "name": "Inkling-Small", "organization": {"slug": "thinkingmachines", "name": "Thinking Machines Lab", "logo_url": "https://thinkingmachines.ai/images/apple-touch-icon.png"}, "family": {"slug": "inkling", "name": "Inkling"}, "url": "/models/thinkingmachines/inkling-small"}, "intelligence_score": 35.2002, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "Inkling Small (XHigh)", "raw_score": 40.138889, "score_unit": "percent", "relative_score": 39.6831, "weight": 0.5, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "Inkling Small; 95% CI [1407.47406284, 1416.83311109]; votes 31473; rank 136", "raw_score": 1412.153587, "score_unit": "rating", "relative_score": 30.7173, "weight": 0.5, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 2, "component_coverage": 0.6667, "missing_components": ["livebench"], "coverage_status": "partial", "score_range": {"lower": 23.4668, "upper": 56.8001}, "intelligence_rank": 31}, {"model": {"canonical_id": "MiniMaxAI/MiniMax-M3", "name": "MiniMax-M3", "organization": {"slug": "minimaxai", "name": "MiniMax", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/676e38ad04af5bec20bc9faf/dUd-LsZEX0H_d4qefO_g6.jpeg"}, "family": {"slug": "minimax-m3", "name": "Minimax M3"}, "url": "/models/minimaxai/minimax-m3"}, "intelligence_score": 33.8637, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "minimax-m3", "raw_score": 70.259864, "score_unit": "percent", "relative_score": 20.6852, "weight": 0.5, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "minimax-m3; 95% CI [1429.60573674, 1437.26171309]; votes 63129; rank 91", "raw_score": 1433.433725, "score_unit": "rating", "relative_score": 47.0422, "weight": 0.5, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 2, "component_coverage": 0.6667, "missing_components": ["arc-agi-2"], "coverage_status": "partial", "score_range": {"lower": 22.5758, "upper": 55.9091}, "intelligence_rank": 32}, {"model": {"canonical_id": "moonshotai/Kimi-K2.7-Code", "name": "Kimi K2.7 Code", "organization": {"slug": "moonshotai", "name": "Moonshot AI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/641c1e77c3983aa9490f8121/X1yT2rsaIbR9cdYGEVu0X.jpeg"}, "family": {"slug": "kimi-k2-7", "name": "Kimi K2 7"}, "url": "/models/moonshotai/kimi-k2-7-code"}, "intelligence_score": 26.9627, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "kimi-k2.7-code", "raw_score": 71.447447, "score_unit": "percent", "relative_score": 26.9627, "weight": 1.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}], "component_count": 1, "component_coverage": 0.3333, "missing_components": ["arc-agi-2", "lmarena-text"], "coverage_status": "partial", "score_range": {"lower": 8.9876, "upper": 75.6542}, "intelligence_rank": 33}, {"model": {"canonical_id": "xai/grok-build-0.1", "name": "Grok Build 0.1", "organization": {"slug": "xai", "name": "xAI", "logo_url": "https://x.ai/favicon.ico"}, "family": {"slug": "grok-build", "name": "Grok Build"}, "url": "/models/xai/grok-build-0-1"}, "intelligence_score": 25.0984, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "grok-build-0.1", "raw_score": 71.094763, "score_unit": "percent", "relative_score": 25.0984, "weight": 1.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}], "component_count": 1, "component_coverage": 0.3333, "missing_components": ["arc-agi-2", "lmarena-text"], "coverage_status": "partial", "score_range": {"lower": 8.3661, "upper": 75.0328}, "intelligence_rank": 34}, {"model": {"canonical_id": "openai/gpt-5.4-mini", "name": "GPT-5.4 Mini", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-5-4", "name": "Gpt 5 4"}, "url": "/models/openai/gpt-5-4-mini"}, "intelligence_score": 20.7753, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "gpt-5.4-mini-xhigh", "raw_score": 69.530263, "score_unit": "percent", "relative_score": 16.8285, "weight": 0.333333, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "GPT-5.4 Mini (XHigh)", "raw_score": 18.9, "score_unit": "percent", "relative_score": 15.2171, "weight": 0.333333, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "gpt-5.4-mini-high; 95% CI [1407.86458416, 1415.30312295]; votes 63461; rank 137", "raw_score": 1411.583854, "score_unit": "rating", "relative_score": 30.2802, "weight": 0.333333, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 3, "component_coverage": 1.0, "missing_components": [], "coverage_status": "complete", "score_range": {"lower": 20.7753, "upper": 20.7753}, "intelligence_rank": 35}, {"model": {"canonical_id": "google-deepmind/gemini-3.5-flash-lite", "name": "Gemini 3.5 Flash-Lite", "organization": {"slug": "google-deepmind", "name": "Google DeepMind", "logo_url": "https://storage.googleapis.com/gdm-deepmind-com-prod-public/icons/google_deepmind_48dp.svg"}, "family": {"slug": "gemini-3", "name": "Gemini 3"}, "url": "/models/google-deepmind/gemini-3-5-flash-lite"}, "intelligence_score": 17.7728, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "gemini-3.5-flash-lite-high", "raw_score": 66.346626, "score_unit": "percent", "relative_score": 0.0, "weight": 0.333333, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "Gemini 3.5 Flash-Lite (High)", "raw_score": 10.277778, "score_unit": "percent", "relative_score": 5.2848, "weight": 0.333333, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "gemini-3.5-flash-lite; 95% CI [1430.26500547, 1439.18690077]; votes 35845; rank 88", "raw_score": 1434.725953, "score_unit": "rating", "relative_score": 48.0336, "weight": 0.333333, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 3, "component_coverage": 1.0, "missing_components": [], "coverage_status": "complete", "score_range": {"lower": 17.7728, "upper": 17.7728}, "intelligence_rank": 36}, {"model": {"canonical_id": "Qwen/Qwen3.5-35B-A3B", "name": "Qwen3.5-35B-A3B", "organization": {"slug": "qwen", "name": "Qwen", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6215ca5692c0ecfba9186921/hrRM50-6XcdWgg2AKpENG.jpeg"}, "family": {"slug": "qwen3-5-35b-a3b", "name": "Qwen3 5 35b A3b"}, "url": "/models/qwen/qwen3-5-35b-a3b"}, "intelligence_score": 17.1865, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "qwen3.5-35b-a3b; 95% CI [1390.31163858, 1398.71981995]; votes 30480; rank 161", "raw_score": 1394.515729, "score_unit": "rating", "relative_score": 17.1865, "weight": 1.0, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 1, "component_coverage": 0.3333, "missing_components": ["livebench", "arc-agi-2"], "coverage_status": "partial", "score_range": {"lower": 5.7288, "upper": 72.3955}, "intelligence_rank": 37}, {"model": {"canonical_id": "openai/gpt-5.4-nano", "name": "GPT-5.4 Nano", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-5-4", "name": "Gpt 5 4"}, "url": "/models/openai/gpt-5-4-nano"}, "intelligence_score": 15.7163, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "gpt-5.4-nano-xhigh", "raw_score": 75.266301, "score_unit": "percent", "relative_score": 47.1489, "weight": 0.333333, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "GPT-5.4 Nano (XHigh)", "raw_score": 5.69, "score_unit": "percent", "relative_score": 0.0, "weight": 0.333333, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "gpt-5.4-nano-high; 95% CI [1368.35606198, 1375.86886621]; votes 62426; rank 181", "raw_score": 1372.112464, "score_unit": "rating", "relative_score": 0.0, "weight": 0.333333, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 3, "component_coverage": 1.0, "missing_components": [], "coverage_status": "complete", "score_range": {"lower": 15.7163, "upper": 15.7163}, "intelligence_rank": 38}, {"model": {"canonical_id": "meta-models/Muse-Glimmer-30B", "name": "Muse Glimmer 30B", "organization": {"slug": "meta-models", "name": "Meta", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/646cf8084eefb026fb8fd8bc/oCTqufkdTkjyGodsx1vo1.png"}, "family": {"slug": "muse-glimmer", "name": "Muse Glimmer"}, "url": "/models/meta-models/muse-glimmer-30b"}, "intelligence_score": 12.8136, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "muse-glimmer; 95% CI [1379.15647412, 1398.47440941]; votes 3889; rank 167", "raw_score": 1388.815442, "score_unit": "rating", "relative_score": 12.8136, "weight": 1.0, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 1, "component_coverage": 0.3333, "missing_components": ["livebench", "arc-agi-2"], "coverage_status": "partial", "score_range": {"lower": 4.2712, "upper": 70.9379}, "intelligence_rank": 39}, {"model": {"canonical_id": "upstage/solar-pro-4", "name": "Solar Pro 4", "organization": {"slug": "upstage", "name": "Upstage", "logo_url": "https://cdn.prod.website-files.com/6743d5190bb2b52f38e99e37/6743f495cc3c0ed693e0b5f3_Logo_Black.avif"}, "family": {"slug": "solar-pro", "name": "Solar Pro"}, "url": "/models/upstage/solar-pro-4"}, "intelligence_score": 11.6926, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "solar-pro4; 95% CI [1382.01330522, 1392.69515195]; votes 20436; rank 168", "raw_score": 1387.354229, "score_unit": "rating", "relative_score": 11.6926, "weight": 1.0, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 1, "component_coverage": 0.3333, "missing_components": ["livebench", "arc-agi-2"], "coverage_status": "partial", "score_range": {"lower": 3.8975, "upper": 70.5642}, "intelligence_rank": 40}, {"model": {"canonical_id": "anthropic/claude-haiku-4-5", "name": "Claude Haiku 4.5", "organization": {"slug": "anthropic", "name": "Anthropic", "logo_url": "https://platform.claude.com/favicon.ico"}, "family": {"slug": "claude-4-5", "name": "Claude 4 5"}, "url": "/models/anthropic/claude-haiku-4-5"}, "intelligence_score": 9.3371, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "Claude Haiku 4.5 (Thinking 32K)", "raw_score": 4.03, "score_unit": "percent", "relative_score": 0.0, "weight": 0.5, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "claude-haiku-4-5-20251001; 95% CI [1394.05523633, 1398.85460008]; votes 148312; rank 158", "raw_score": 1396.454918, "score_unit": "rating", "relative_score": 18.6742, "weight": 0.5, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 2, "component_coverage": 0.6667, "missing_components": ["livebench"], "coverage_status": "partial", "score_range": {"lower": 6.2247, "upper": 39.5581}, "intelligence_rank": 41}, {"model": {"canonical_id": "deepseek-ai/DeepSeek-R1", "name": "DeepSeek-R1", "organization": {"slug": "deepseek-ai", "name": "DeepSeek", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6538815d1bdb3c40db94fbfa/xMBly9PUMphrFVMxLX4kq.png"}, "family": {"slug": "deepseek-r1", "name": "Deepseek R1"}, "url": "/models/deepseek-ai/deepseek-r1"}, "intelligence_score": 0.3936, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "deepseek-r1; 95% CI [1367.77932247, 1377.47177255]; votes 18524; rank 180", "raw_score": 1372.625548, "score_unit": "rating", "relative_score": 0.3936, "weight": 1.0, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 1, "component_coverage": 0.3333, "missing_components": ["livebench", "arc-agi-2"], "coverage_status": "partial", "score_range": {"lower": 0.1312, "upper": 66.7979}, "intelligence_rank": 42}, {"model": {"canonical_id": "allenai/Olmo-3-32B-Think", "name": "Olmo-3-32B-Think", "organization": {"slug": "allenai", "name": "Ai2", "logo_url": "https://allenai.org/icon.png"}, "family": {"slug": "olmo-3-32b-think", "name": "Olmo 3 32b Think"}, "url": "/models/allenai/olmo-3-32b-think"}, "intelligence_score": 0.0, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "olmo-3-32b-think; 95% CI [1291.24080187, 1307.72424991]; votes 5829; rank 247", "raw_score": 1299.482526, "score_unit": "rating", "relative_score": 0.0, "weight": 1.0, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 1, "component_coverage": 0.3333, "missing_components": ["livebench", "arc-agi-2"], "coverage_status": "partial", "score_range": {"lower": 0.0, "upper": 66.6667}, "intelligence_rank": 43}, {"model": {"canonical_id": "amazon/nova-2-lite-v1:0", "name": "Nova 2 Lite", "organization": {"slug": "amazon", "name": "Amazon", "logo_url": "https://aws.amazon.com/favicon.ico"}, "family": {"slug": "nova-2", "name": "Nova 2"}, "url": "/models/amazon/nova-2-lite-v1-0"}, "intelligence_score": 0.0, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "nova-2-lite; 95% CI [1355.82103717, 1367.83657160]; votes 12414; rank 194", "raw_score": 1361.828804, "score_unit": "rating", "relative_score": 0.0, "weight": 1.0, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 1, "component_coverage": 0.3333, "missing_components": ["livebench", "arc-agi-2"], "coverage_status": "partial", "score_range": {"lower": 0.0, "upper": 66.6667}, "intelligence_rank": 43}, {"model": {"canonical_id": "coherelabs/command-a-03-2025", "name": "Command A", "organization": {"slug": "coherelabs", "name": "Cohere", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678549441248-5e70f6048ce3c604d78fe133.png"}, "family": {"slug": "command-a", "name": "Command A"}, "url": "/models/coherelabs/command-a-03-2025"}, "intelligence_score": 0.0, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "command-a-03-2025; 95% CI [1327.48678451, 1334.38311976]; votes 55762; rank 224", "raw_score": 1330.934952, "score_unit": "rating", "relative_score": 0.0, "weight": 1.0, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 1, "component_coverage": 0.3333, "missing_components": ["livebench", "arc-agi-2"], "coverage_status": "partial", "score_range": {"lower": 0.0, "upper": 66.6667}, "intelligence_rank": 43}, {"model": {"canonical_id": "ibm-granite/granite-4.2-30b", "name": "Granite 4.2 30B", "organization": {"slug": "ibm-granite", "name": "IBM", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/639bcaa2445b133a4e942436/CEW-OjXkRkDNmTxSu8Egh.png"}, "family": {"slug": "granite-4-2", "name": "Granite 4 2"}, "url": "/models/ibm-granite/granite-4-2-30b"}, "intelligence_score": 0.0, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "granite-4.2-30b; 95% CI [1350.75469951, 1371.60664245]; votes 3405; rank 196", "raw_score": 1361.180671, "score_unit": "rating", "relative_score": 0.0, "weight": 1.0, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 1, "component_coverage": 0.3333, "missing_components": ["livebench", "arc-agi-2"], "coverage_status": "partial", "score_range": {"lower": 0.0, "upper": 66.6667}, "intelligence_rank": 43}, {"model": {"canonical_id": "ibm-granite/granite-4.2-3b", "name": "Granite 4.2 3B", "organization": {"slug": "ibm-granite", "name": "IBM", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/639bcaa2445b133a4e942436/CEW-OjXkRkDNmTxSu8Egh.png"}, "family": {"slug": "granite-4-2", "name": "Granite 4 2"}, "url": "/models/ibm-granite/granite-4-2-3b"}, "intelligence_score": 0.0, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "granite-4.2-3b; 95% CI [1281.12348623, 1304.12939318]; votes 3250; rank 252", "raw_score": 1292.62644, "score_unit": "rating", "relative_score": 0.0, "weight": 1.0, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 1, "component_coverage": 0.3333, "missing_components": ["livebench", "arc-agi-2"], "coverage_status": "partial", "score_range": {"lower": 0.0, "upper": 66.6667}, "intelligence_rank": 43}, {"model": {"canonical_id": "ibm-granite/granite-4.2-8b", "name": "Granite 4.2 8B", "organization": {"slug": "ibm-granite", "name": "IBM", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/639bcaa2445b133a4e942436/CEW-OjXkRkDNmTxSu8Egh.png"}, "family": {"slug": "granite-4-2", "name": "Granite 4 2"}, "url": "/models/ibm-granite/granite-4-2-8b"}, "intelligence_score": 0.0, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "granite-4.2-8b; 95% CI [1308.51408521, 1330.64459541]; votes 3255; rank 233", "raw_score": 1319.57934, "score_unit": "rating", "relative_score": 0.0, "weight": 1.0, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 1, "component_coverage": 0.3333, "missing_components": ["livebench", "arc-agi-2"], "coverage_status": "partial", "score_range": {"lower": 0.0, "upper": 66.6667}, "intelligence_rank": 43}, {"model": {"canonical_id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct", "name": "Llama-4-Maverick-17B-128E-Instruct", "organization": {"slug": "meta-llama", "name": "Meta", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/646cf8084eefb026fb8fd8bc/oCTqufkdTkjyGodsx1vo1.png"}, "family": {"slug": "llama-4-maverick-17b-128e-instruct", "name": "Llama 4 Maverick 17b 128e Instruct"}, "url": "/models/meta-llama/llama-4-maverick-17b-128e-instruct"}, "intelligence_score": 0.0, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "llama-4-maverick-17b-128e-instruct; 95% CI [1282.86234604, 1291.36961888]; votes 39450; rank 260", "raw_score": 1287.115982, "score_unit": "rating", "relative_score": 0.0, "weight": 1.0, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 1, "component_coverage": 0.3333, "missing_components": ["livebench", "arc-agi-2"], "coverage_status": "partial", "score_range": {"lower": 0.0, "upper": 66.6667}, "intelligence_rank": 43}, {"model": {"canonical_id": "meta-llama/Llama-4-Scout-17B-16E-Instruct", "name": "Llama-4-Scout-17B-16E-Instruct", "organization": {"slug": "meta-llama", "name": "Meta", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/646cf8084eefb026fb8fd8bc/oCTqufkdTkjyGodsx1vo1.png"}, "family": {"slug": "llama-4-scout-17b-16e-instruct", "name": "Llama 4 Scout 17b 16e Instruct"}, "url": "/models/meta-llama/llama-4-scout-17b-16e-instruct"}, "intelligence_score": 0.0, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "llama-4-scout-17b-16e-instruct; 95% CI [1274.44593166, 1283.86713951]; votes 29830; rank 272", "raw_score": 1279.156536, "score_unit": "rating", "relative_score": 0.0, "weight": 1.0, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 1, "component_coverage": 0.3333, "missing_components": ["livebench", "arc-agi-2"], "coverage_status": "partial", "score_range": {"lower": 0.0, "upper": 66.6667}, "intelligence_rank": 43}, {"model": {"canonical_id": "microsoft/phi-4", "name": "phi-4", "organization": {"slug": "microsoft", "name": "Microsoft", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/1583646260758-5e64858c87403103f9f1055d.png"}, "family": {"slug": "phi-4", "name": "Phi 4"}, "url": "/models/microsoft/phi-4"}, "intelligence_score": 0.0, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "phi-4; 95% CI [1212.04973336, 1221.21224665]; votes 24126; rank 313", "raw_score": 1216.63099, "score_unit": "rating", "relative_score": 0.0, "weight": 1.0, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 1, "component_coverage": 0.3333, "missing_components": ["livebench", "arc-agi-2"], "coverage_status": "partial", "score_range": {"lower": 0.0, "upper": 66.6667}, "intelligence_rank": 43}, {"model": {"canonical_id": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16", "name": "NVIDIA-Nemotron-3-Nano-30B-A3B-BF16", "organization": {"slug": "nvidia", "name": "NVIDIA", "logo_url": "https://www.nvidia.com/etc/designs/nvidiaGDC/clientlibs_base/images/NVIDIA-Logo.svg"}, "family": {"slug": "nvidia-nemotron-3-nano-30b-a3b-bf16", "name": "Nvidia Nemotron 3 Nano 30b A3b Bf16"}, "url": "/models/nvidia/nvidia-nemotron-3-nano-30b-a3b-bf16"}, "intelligence_score": 0.0, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "nvidia-nemotron-3-nano-30b-a3b-bf16; 95% CI [1342.44535387, 1353.21593076]; votes 15774; rank 208", "raw_score": 1347.830642, "score_unit": "rating", "relative_score": 0.0, "weight": 1.0, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 1, "component_coverage": 0.3333, "missing_components": ["livebench", "arc-agi-2"], "coverage_status": "partial", "score_range": {"lower": 0.0, "upper": 66.6667}, "intelligence_rank": 43}, {"model": {"canonical_id": "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16", "name": "NVIDIA Nemotron 3.5 Lightning 30B-A3B", "organization": {"slug": "nvidia", "name": "NVIDIA", "logo_url": "https://www.nvidia.com/etc/designs/nvidiaGDC/clientlibs_base/images/NVIDIA-Logo.svg"}, "family": {"slug": "nvidia-nemotron-3-5-lightning", "name": "Nvidia Nemotron 3 5 Lightning"}, "url": "/models/nvidia/nvidia-nemotron-3-5-lightning-30b-a3b-bf16"}, "intelligence_score": 0.0, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "nvidia-nemotron-3.5-lightning-30b-a3b-nvfp4; 95% CI [1323.19858715, 1334.38208235]; votes 19080; rank 228", "raw_score": 1328.790335, "score_unit": "rating", "relative_score": 0.0, "weight": 1.0, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 1, "component_coverage": 0.3333, "missing_components": ["livebench", "arc-agi-2"], "coverage_status": "partial", "score_range": {"lower": 0.0, "upper": 66.6667}, "intelligence_rank": 43}, {"model": {"canonical_id": "openai/gpt-4o", "name": "GPT-4o", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-4o", "name": "Gpt 4o"}, "url": "/models/openai/gpt-4o"}, "intelligence_score": 0.0, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "gpt-4o-2024-08-06; 95% CI [1278.30330239, 1286.68377978]; votes 45499; rank 266", "raw_score": 1282.493541, "score_unit": "rating", "relative_score": 0.0, "weight": 1.0, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 1, "component_coverage": 0.3333, "missing_components": ["livebench", "arc-agi-2"], "coverage_status": "partial", "score_range": {"lower": 0.0, "upper": 66.6667}, "intelligence_rank": 43}, {"model": {"canonical_id": "openai/gpt-4o-mini", "name": "GPT-4o Mini", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-4o", "name": "Gpt 4o"}, "url": "/models/openai/gpt-4o-mini"}, "intelligence_score": 0.0, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "gpt-4o-mini-2024-07-18; 95% CI [1282.80560399, 1289.84597308]; votes 68705; rank 262", "raw_score": 1286.325789, "score_unit": "rating", "relative_score": 0.0, "weight": 1.0, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 1, "component_coverage": 0.3333, "missing_components": ["livebench", "arc-agi-2"], "coverage_status": "partial", "score_range": {"lower": 0.0, "upper": 66.6667}, "intelligence_rank": 43}, {"model": {"canonical_id": "openai/gpt-oss-120b", "name": "gpt-oss-120b", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-oss-120b", "name": "Gpt Oss 120b"}, "url": "/models/openai/gpt-oss-120b"}, "intelligence_score": 0.0, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "gpt-oss-120b; 95% CI [1361.09785146, 1369.79086069]; votes 30214; rank 191", "raw_score": 1365.444356, "score_unit": "rating", "relative_score": 0.0, "weight": 1.0, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 1, "component_coverage": 0.3333, "missing_components": ["livebench", "arc-agi-2"], "coverage_status": "partial", "score_range": {"lower": 0.0, "upper": 66.6667}, "intelligence_rank": 43}, {"model": {"canonical_id": "openai/gpt-oss-20b", "name": "gpt-oss-20b", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-oss", "name": "Gpt Oss"}, "url": "/models/openai/gpt-oss-20b"}, "intelligence_score": 0.0, "index_version": "4.4", "profile": "relative English-language model performance and preference", "components": [{"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "gpt-oss-20b; 95% CI [1281.01874821, 1293.79533494]; votes 10421; rank 259", "raw_score": 1287.407042, "score_unit": "rating", "relative_score": 0.0, "weight": 1.0, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "component_count": 1, "component_coverage": 0.3333, "missing_components": ["livebench", "arc-agi-2"], "coverage_status": "partial", "score_range": {"lower": 0.0, "upper": 66.6667}, "intelligence_rank": 43}], "intelligence_index": {"name": "MM Relative Intelligence Index", "short_name": "MM Intelligence", "version": "4.4", "profile": "relative English-language model performance and preference", "status": "ready", "method": "Equal-weight mean of available LiveBench, ARC-AGI-2, and LMArena Text original-publisher scores linearly normalized to the frozen 20-model reference range. At least one of three components is required; one- and two-source rows are provisional with explicit coverage bounds. LMArena Text measures human preference, not objective task success. Default ranks include only reviewed current product-line generations.", "minimum_component_count": 1, "coverage_range_method": "Hold observed components fixed; let each missing component range from 0 to 100 in the full three-source mean. These are coverage bounds, not confidence intervals.", "tie_method": "Equal scores at four decimal places share a competition rank; coverage then canonical ID determine display order only.", "lifecycle_scope": "Reviewed current product-line generations that are active or preview with at least one currently available provider endpoint.", "reference_cohort_size": 20, "reference_cohort": ["anthropic/claude-opus-4-6", "anthropic/claude-opus-4-7", "anthropic/claude-opus-4-8", "anthropic/claude-opus-5", "anthropic/claude-sonnet-4-6", "deepseek-ai/DeepSeek-V4-Flash", "google-deepmind/gemini-3.5-flash", "google-deepmind/gemini-3.5-flash-lite", "google-deepmind/gemini-3.6-flash", "google-deepmind/gemini-3.7-flash", "moonshotai/Kimi-K3", "openai/gpt-5.2", "openai/gpt-5.4", "openai/gpt-5.4-mini", "openai/gpt-5.4-nano", "openai/gpt-5.5", "openai/gpt-5.6-luna", "openai/gpt-5.6-sol", "openai/gpt-5.6-terra", "xai/grok-4.5"], "observed_at": "2026-10-15T11:14:08+00:00", "components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "artifact_sha256": "09d810986777c92b75b40a58a1829e0318e34cb5693ecae970b3145852271ba7", "archive_sha256": "86566f9414c04eb9025b05f11e900cf00c85436df12484f2de73f8ed17fa45e7", "weight": 0.333333, "reference_lower": 66.34662598, "reference_upper": 85.26472441, "observed_at": "2026-10-15T12:46:28.151878+00:00"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "artifact_sha256": "4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee", "archive_sha256": "596442f082c5a2ca0c89078258dc4408424f4e3510756c6c48ec5235dbd14e65", "weight": 0.333333, "reference_lower": 5.69, "reference_upper": 92.5, "observed_at": "2026-10-15T11:14:08+00:00"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "artifact_sha256": "e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0", "archive_sha256": "1cc6058242dfdcdf5a15aa1ca2cd25ce8235dab55af155bc0af11fbbc1b4772a", "weight": 0.333333, "reference_lower": 45.737082136333335, "reference_upper": 50.082203056, "observed_at": "2026-10-15T11:14:08+00:00"}], "eligible_model_count": 57}, "performance": [{"model": {"canonical_id": "anthropic/claude-fable-5-1", "name": "Claude Fable 5.1", "organization": {"slug": "anthropic", "name": "Anthropic", "logo_url": "https://platform.claude.com/favicon.ico"}, "family": {"slug": "claude-5-1", "name": "Claude 5 1"}, "url": "/models/anthropic/claude-fable-5-1"}, "performance_score": 71.8986, "efficiency_score": 3.3468, "efficiency_performance_score": 99.1854, "average_output_tokens": 42561.5, "benchmark_count": 8, "performance_scope": "arc-agi-1+arc-agi-2+livebench+lmarena-agent+lmarena-document+lmarena-search+lmarena-vision+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.7273, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "Claude Fable 5.1 (Max)", "score": 97.5, "normalized_score": 97.5, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "Claude Fable 5.1 (XHigh)", "score": 90.0, "normalized_score": 90.0, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "claude-fable-5-1-max-effort", "score": 86.816836, "normalized_score": 86.816836, "output_tokens_per_case": 16470.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-agent", "version": "agent-2026-10-16-a64ca3b12b6e", "configuration": "Claude Fable 5.1 (Max); 95% CI [12.03932907, 16.02502568]; sessions 16374; observations 1913479; rank 3", "score": 14.032177, "normalized_score": 57.016089, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/agent/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-document", "version": "document-2026-09-13-a64ca3b12b6e", "configuration": "claude-fable-5.1-max; 95% CI [1497.40364732, 1527.76498981]; votes 1403; rank 2", "score": 1512.584319, "normalized_score": 50.419477, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/document/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-search", "version": "search-2026-10-13-a64ca3b12b6e", "configuration": "claude-fable-5.1-high; 95% CI [1238.79268797, 1252.89817971]; votes 12782; rank 5", "score": 1245.845434, "normalized_score": 41.528181, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/search/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "claude-fable-5.1-max; 95% CI [1308.61778049, 1327.86146111]; votes 4648; rank 4", "score": 1318.239621, "normalized_score": 43.941321, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Claude Fable 5.1 (max effort)", "score": 84.53, "normalized_score": 84.53, "output_tokens_per_case": 68653.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 1, "efficiency_rank": 26}, {"model": {"canonical_id": "openai/gpt-6-astra", "name": "GPT-6 Astra", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-6", "name": "Gpt 6"}, "url": "/models/openai/gpt-6-astra"}, "performance_score": 71.3396, "efficiency_score": 6.8414, "efficiency_performance_score": 97.7003, "average_output_tokens": 15428.0, "benchmark_count": 8, "performance_scope": "arc-agi-1+arc-agi-2+livebench+lmarena-document+lmarena-search+lmarena-text+lmarena-vision+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.7273, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "GPT-6 Astra (XHigh)", "score": 98.5, "normalized_score": 98.5, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "GPT-6 Astra (Max)", "score": 95.0, "normalized_score": 95.0, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "gpt-6-astra-max", "score": 86.47107, "normalized_score": 86.47107, "output_tokens_per_case": 10407.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-document", "version": "document-2026-09-13-a64ca3b12b6e", "configuration": "gpt-6-astra-max; 95% CI [1453.25995337, 1481.78626802]; votes 1621; rank 16", "score": 1467.523111, "normalized_score": 48.917437, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/document/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-search", "version": "search-2026-10-13-a64ca3b12b6e", "configuration": "gpt-6-astra-max; 95% CI [1225.77363708, 1241.45798456]; votes 18483; rank 7", "score": 1233.615811, "normalized_score": 41.120527, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/search/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "gpt-6-astra-max; 95% CI [1436.40189535, 1448.98654490]; votes 12163; rank 69", "score": 1442.69422, "normalized_score": 48.089807, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "gpt-6-astra-max; 95% CI [1270.63592513, 1292.07239183]; votes 3590; rank 36", "score": 1281.354158, "normalized_score": 42.711805, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "GPT-6 Astra (max)", "score": 82.32, "normalized_score": 82.32, "output_tokens_per_case": 20449.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 2, "efficiency_rank": 17}, {"model": {"canonical_id": "google-deepmind/gemini-3.1-pro-preview", "name": "Gemini 3.1 Pro", "organization": {"slug": "google-deepmind", "name": "Google DeepMind", "logo_url": "https://storage.googleapis.com/gdm-deepmind-com-prod-public/icons/google_deepmind_48dp.svg"}, "family": {"slug": "gemini-3", "name": "Gemini 3"}, "url": "/models/google-deepmind/gemini-3-1-pro-preview"}, "performance_score": 66.4669, "efficiency_score": 8.1208, "efficiency_performance_score": 88.3373, "average_output_tokens": 11704.5, "benchmark_count": 8, "performance_scope": "arc-agi-1+arc-agi-2+livebench+lmarena-agent+lmarena-document+lmarena-search+lmarena-vision+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.7273, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "Gemini 3.1 Pro (Preview)", "score": 98.0, "normalized_score": 98.0, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "Gemini 3.1 Pro (Preview)", "score": 77.08, "normalized_score": 77.08, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "gemini-3.1-pro-preview-high", "score": 81.660565, "normalized_score": 81.660565, "output_tokens_per_case": 13380.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-agent", "version": "agent-2026-10-16-a64ca3b12b6e", "configuration": "Gemini 3.1 Pro Preview; 95% CI [-5.35690873, -2.63856355]; sessions 87236; observations 2815597; rank 39", "score": -3.997736, "normalized_score": 48.001132, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/agent/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-document", "version": "document-2026-09-13-a64ca3b12b6e", "configuration": "gemini-3.1-pro-preview; 95% CI [1438.69417039, 1449.14324048]; votes 49457; rank 31", "score": 1443.918705, "normalized_score": 48.130624, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/document/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-search", "version": "search-2026-10-13-a64ca3b12b6e", "configuration": "gemini-3.1-pro-grounding; 95% CI [1204.12797055, 1213.48336905]; votes 151436; rank 15", "score": 1208.80567, "normalized_score": 40.293522, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/search/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "gemini-3.1-pro-preview; 95% CI [1291.04958388, 1301.35691905]; votes 46320; rank 22", "score": 1296.203251, "normalized_score": 43.206775, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Gemini 3.1 Pro (high thinking)", "score": 70.99, "normalized_score": 70.99, "output_tokens_per_case": 10029.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 3, "efficiency_rank": 16}, {"model": {"canonical_id": "openai/gpt-6.1-sol", "name": "GPT-6.1 Sol", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-6", "name": "Gpt 6"}, "url": "/models/openai/gpt-6.1-sol"}, "performance_score": 62.4917, "efficiency_score": 6.7327, "efficiency_performance_score": 97.5789, "average_output_tokens": 15798.0, "benchmark_count": 7, "performance_scope": "arc-agi-1+arc-agi-2+livebench+lmarena-search+lmarena-text+lmarena-vision+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.6364, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "GPT-6.1 Sol (XHigh)", "score": 98.5, "normalized_score": 98.5, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "GPT-6.1 Sol (Max)", "score": 94.166667, "normalized_score": 94.166667, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "gpt-6.1-sol-max", "score": 86.138965, "normalized_score": 86.138965, "output_tokens_per_case": 10375.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-search", "version": "search-2026-10-13-a64ca3b12b6e", "configuration": "gpt-6.1-sol-max; 95% CI [1224.24145466, 1241.96324521]; votes 5555; rank 8", "score": 1233.10235, "normalized_score": 41.103412, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/search/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "gpt-6.1-sol-max; 95% CI [1439.59979847, 1455.74908604]; votes 6320; rank 57", "score": 1447.674442, "normalized_score": 48.255815, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "gpt-6.1-sol-max; 95% CI [1273.83724449, 1302.54208160]; votes 1813; rank 30", "score": 1288.189663, "normalized_score": 42.939655, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "GPT-6.1 Sol (max)", "score": 82.44, "normalized_score": 82.44, "output_tokens_per_case": 21221.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 4, "efficiency_rank": 18}, {"model": {"canonical_id": "openai/gpt-5.6-terra", "name": "GPT-5.6 Terra", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-5-6", "name": "Gpt 5 6"}, "url": "/models/openai/gpt-5-6-terra"}, "performance_score": 60.6496, "efficiency_score": 4.6589, "efficiency_performance_score": 94.7709, "average_output_tokens": 21431.5, "benchmark_count": 7, "performance_scope": "arc-agi-1+arc-agi-2+livebench+lmarena-document+lmarena-text+lmarena-vision+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.6364, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "GPT-5.6 Terra (Max)", "score": 96.5, "normalized_score": 96.5, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "GPT-5.6 Terra (Max)", "score": 83.9, "normalized_score": 83.9, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "gpt-5.6-terra-max", "score": 82.314061, "normalized_score": 82.314061, "output_tokens_per_case": 22145.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-document", "version": "document-2026-09-13-a64ca3b12b6e", "configuration": "gpt-5.6-terra-xhigh; 95% CI [1463.31179298, 1479.85049651]; votes 5787; rank 13", "score": 1471.581145, "normalized_score": 49.052705, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/document/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "gpt-5.6-terra-xhigh; 95% CI [1443.15823569, 1451.62460535]; votes 43271; rank 58", "score": 1447.391421, "normalized_score": 48.246381, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "gpt-5.6-terra-xhigh; 95% CI [1263.65540928, 1278.48964371]; votes 11020; rank 43", "score": 1271.072527, "normalized_score": 42.369084, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "GPT-5.6 Terra (ultra)", "score": 81.4, "normalized_score": 81.4, "output_tokens_per_case": 20718.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 5, "efficiency_rank": 20}, {"model": {"canonical_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "organization": {"slug": "anthropic", "name": "Anthropic", "logo_url": "https://platform.claude.com/favicon.ico"}, "family": {"slug": "claude-5", "name": "Claude 5"}, "url": "/models/anthropic/claude-sonnet-5"}, "performance_score": 51.5341, "efficiency_score": 2.781, "efficiency_performance_score": 92.1724, "average_output_tokens": 43190.5, "benchmark_count": 6, "performance_scope": "livebench+lmarena-agent+lmarena-document+lmarena-text+lmarena-vision+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.5455, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "claude-sonnet-5-xhigh-effort", "score": 80.014756, "normalized_score": 80.014756, "output_tokens_per_case": 19428.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-agent", "version": "agent-2026-10-16-a64ca3b12b6e", "configuration": "Claude Sonnet 5 (High); 95% CI [2.88280252, 6.28024714]; sessions 33276; observations 3570560; rank 12", "score": 4.581525, "normalized_score": 52.290762, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/agent/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-document", "version": "document-2026-09-13-a64ca3b12b6e", "configuration": "claude-sonnet-5-high; 95% CI [1458.49407458, 1473.77896309]; votes 7411; rank 17", "score": 1466.136519, "normalized_score": 48.871217, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/document/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "claude-sonnet-5-high; 95% CI [1438.01344792, 1446.22951308]; votes 49595; rank 72", "score": 1442.12148, "normalized_score": 48.070716, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "claude-sonnet-5-high; 95% CI [1267.02186706, 1280.81063637]; votes 13503; rank 41", "score": 1273.916252, "normalized_score": 42.463875, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Claude Sonnet 5 (max effort)", "score": 79.21, "normalized_score": 79.21, "output_tokens_per_case": 66953.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 6, "efficiency_rank": 27}, {"model": {"canonical_id": "google-deepmind/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "organization": {"slug": "google-deepmind", "name": "Google DeepMind", "logo_url": "https://storage.googleapis.com/gdm-deepmind-com-prod-public/icons/google_deepmind_48dp.svg"}, "family": {"slug": "gemini-3", "name": "Gemini 3"}, "url": "/models/google-deepmind/gemini-3-8-flash"}, "performance_score": 50.8525, "efficiency_score": 3.4576, "efficiency_performance_score": 87.4253, "average_output_tokens": 31577.5, "benchmark_count": 6, "performance_scope": "arc-agi-1+arc-agi-2+livebench+lmarena-agent+lmarena-vision+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.5455, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "Gemini 3.8 Flash (High)", "score": 98.5, "normalized_score": 98.5, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "Gemini 3.8 Flash (High)", "score": 89.166667, "normalized_score": 89.166667, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "gemini-3.8-flash-high", "score": 80.854991, "normalized_score": 80.854991, "output_tokens_per_case": 42786.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-agent", "version": "agent-2026-10-16-a64ca3b12b6e", "configuration": "Gemini 3.8 Flash (High); 95% CI [2.64957678, 4.84993702]; sessions 37692; observations 5316787; rank 15", "score": 3.749757, "normalized_score": 51.874878, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/agent/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "gemini-3.8-flash-high; 95% CI [1303.54395703, 1324.61562115]; votes 3792; rank 8", "score": 1314.079789, "normalized_score": 43.80266, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Gemini 3.8 Flash (high thinking)", "score": 70.22, "normalized_score": 70.22, "output_tokens_per_case": 20369.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 7, "efficiency_rank": 25}, {"model": {"canonical_id": "openai/gpt-6-luna", "name": "GPT-6 Luna", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-6", "name": "Gpt 6"}, "url": "/models/openai/gpt-6-luna"}, "performance_score": 46.7777, "efficiency_score": 9.8763, "efficiency_performance_score": 89.1728, "average_output_tokens": 21232.0, "benchmark_count": 6, "performance_scope": "arc-agi-1+arc-agi-2+livebench+lmarena-search+lmarena-text+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.5455, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "GPT-6 Luna (Max)", "score": 86.666667, "normalized_score": 86.666667, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "GPT-6 Luna (Max)", "score": 59.305556, "normalized_score": 59.305556, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "gpt-6-luna-max", "score": 75.837013, "normalized_score": 75.837013, "output_tokens_per_case": 35869.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-search", "version": "search-2026-10-13-a64ca3b12b6e", "configuration": "gpt-6-luna-max; 95% CI [1152.33057533, 1166.78316335]; votes 10793; rank 32", "score": 1159.556869, "normalized_score": 38.651896, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/search/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "gpt-6-luna-max; 95% CI [1387.01005073, 1396.24774606]; votes 49617; rank 166", "score": 1391.628898, "normalized_score": 46.38763, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "GPT-6 Luna (max)", "score": 78.19, "normalized_score": 78.19, "output_tokens_per_case": 6595.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 8, "efficiency_rank": 14}, {"model": {"canonical_id": "anthropic/claude-opus-5-5", "name": "Claude Opus 5.5", "organization": {"slug": "anthropic", "name": "Anthropic", "logo_url": "https://platform.claude.com/favicon.ico"}, "family": {"slug": "claude-5-5", "name": "Claude 5 5"}, "url": "/models/anthropic/claude-opus-5-5"}, "performance_score": 44.855, "efficiency_score": 2.0522, "efficiency_performance_score": 99.4958, "average_output_tokens": 76047.5, "benchmark_count": 5, "performance_scope": "arc-agi-1+arc-agi-2+livebench+lmarena-search+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.4545, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "Claude Opus 5.5 (High)", "score": 98.5, "normalized_score": 98.5, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "Claude Opus 5.5 (High)", "score": 93.333333, "normalized_score": 93.333333, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "claude-opus-5-5-max-effort", "score": 85.941291, "normalized_score": 85.941291, "output_tokens_per_case": 25610.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-search", "version": "search-2026-10-13-a64ca3b12b6e", "configuration": "claude-opus-5.5-medium; 95% CI [1205.66309681, 1219.84195206]; votes 10842; rank 14", "score": 1212.752524, "normalized_score": 40.425084, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/search/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Claude Opus 5.5 (max effort)", "score": 85.93, "normalized_score": 85.93, "output_tokens_per_case": 126485.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 9, "efficiency_rank": 31}, {"model": {"canonical_id": "qwen/qwen3.8-max", "name": "Qwen3.8-Max", "organization": {"slug": "qwen", "name": "Qwen", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6215ca5692c0ecfba9186921/hrRM50-6XcdWgg2AKpENG.jpeg"}, "family": {"slug": "qwen3-8-max", "name": "Qwen3 8 Max"}, "url": "/models/qwen/qwen3-8-max"}, "performance_score": 43.9428, "efficiency_score": 3.6727, "efficiency_performance_score": 91.8615, "average_output_tokens": 25738.0, "benchmark_count": 5, "performance_scope": "livebench+lmarena-search+lmarena-text+lmarena-vision+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.4545, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "qwen3.8-max", "score": 81.879613, "normalized_score": 81.879613, "output_tokens_per_case": 21637.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-search", "version": "search-2026-10-13-a64ca3b12b6e", "configuration": "qwen3.8-max; 95% CI [1247.89214823, 1274.26022415]; votes 1870; rank 2", "score": 1261.076186, "normalized_score": 42.035873, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/search/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "qwen3.8-max; 95% CI [1477.92809424, 1487.82635626]; votes 27766; rank 17", "score": 1482.877225, "normalized_score": 49.429241, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "qwen3.8-max; 95% CI [1306.14335895, 1321.05468944]; votes 10017; rank 9", "score": 1313.599024, "normalized_score": 43.786634, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Qwen3.8 Max (thinking on)", "score": 76.83, "normalized_score": 76.83, "output_tokens_per_case": 29839.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 10, "efficiency_rank": 23}, {"model": {"canonical_id": "thinkingmachines/Inkling", "name": "Inkling", "organization": {"slug": "thinkingmachines", "name": "Thinking Machines Lab", "logo_url": "https://thinkingmachines.ai/images/apple-touch-icon.png"}, "family": {"slug": "inkling", "name": "Inkling"}, "url": "/models/thinkingmachines/inkling"}, "performance_score": 41.7806, "efficiency_score": 8.9628, "efficiency_performance_score": 84.0566, "average_output_tokens": 14605.5, "benchmark_count": 6, "performance_scope": "arc-agi-1+arc-agi-2+livebench+lmarena-agent+lmarena-text+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.5455, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "Inkling", "score": 79.5, "normalized_score": 79.5, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "Inkling", "score": 36.527778, "normalized_score": 36.527778, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "inkling-xhigh", "score": 76.470779, "normalized_score": 76.470779, "output_tokens_per_case": 22213.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-agent", "version": "agent-2026-10-16-a64ca3b12b6e", "configuration": "Inkling; 95% CI [-15.81859883, -12.88168979]; sessions 43507; observations 1662352; rank 50", "score": -14.350144, "normalized_score": 42.824928, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/agent/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "inkling; 95% CI [1437.08506747, 1445.68368363]; votes 40648; rank 74", "score": 1441.384376, "normalized_score": 48.046146, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Inkling (high)", "score": 68.77, "normalized_score": 68.77, "output_tokens_per_case": 6998.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 11, "efficiency_rank": 15}, {"model": {"canonical_id": "MiniMaxAI/MiniMax-M3", "name": "MiniMax-M3", "organization": {"slug": "minimaxai", "name": "MiniMax", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/676e38ad04af5bec20bc9faf/dUd-LsZEX0H_d4qefO_g6.jpeg"}, "family": {"slug": "minimax-m3", "name": "Minimax M3"}, "url": "/models/minimaxai/minimax-m3"}, "performance_score": 41.3218, "efficiency_score": 3.8465, "efficiency_performance_score": 83.9824, "average_output_tokens": 23653.5, "benchmark_count": 5, "performance_scope": "livebench+lmarena-document+lmarena-text+lmarena-vision+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.4545, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "minimax-m3", "score": 70.259864, "normalized_score": 70.259864, "output_tokens_per_case": 15530.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-document", "version": "document-2026-09-13-a64ca3b12b6e", "configuration": "minimax-m3; 95% CI [1426.53255805, 1443.05504941]; votes 6314; rank 32", "score": 1434.793804, "normalized_score": 47.82646, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/document/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "minimax-m3; 95% CI [1429.51159020, 1437.14164071]; votes 63973; rank 91", "score": 1433.326615, "normalized_score": 47.777554, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "minimax-m3; 95% CI [1246.68252453, 1259.53765792]; votes 19026; rank 60", "score": 1253.110091, "normalized_score": 41.770336, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "MiniMax M3 (thinking on)", "score": 74.79, "normalized_score": 74.79, "output_tokens_per_case": 31777.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 12, "efficiency_rank": 22}, {"model": {"canonical_id": "xai/grok-4.20-multi-agent-0309", "name": "Grok 4.20 Multi-Agent", "organization": {"slug": "xai", "name": "xAI", "logo_url": "https://x.ai/favicon.ico"}, "family": {"slug": "grok-4-20", "name": "Grok 4 20"}, "url": "/models/xai/grok-4-20-multi-agent-0309"}, "performance_score": 40.7522, "efficiency_score": null, "efficiency_performance_score": null, "average_output_tokens": null, "benchmark_count": 5, "performance_scope": "arc-agi-1+arc-agi-2+lmarena-search+lmarena-text+lmarena-vision", "efficiency_scope": null, "efficiency_benchmark_count": 0, "coverage": 0.4545, "efficiency_coverage": 0.0, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "Grok 4.20 (Reasoning)", "score": 89.5, "normalized_score": 89.5, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "Grok 4.20 (Reasoning)", "score": 65.14, "normalized_score": 65.14, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-search", "version": "search-2026-10-13-a64ca3b12b6e", "configuration": "grok-4.20-multi-agent-beta-0309; 95% CI [1199.36322528, 1210.23649279]; votes 126238; rank 18", "score": 1204.799859, "normalized_score": 40.159995, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/search/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "grok-4.20-multi-agent-beta-0309; 95% CI [1446.59423552, 1453.95404223]; votes 64946; rank 52", "score": 1450.274139, "normalized_score": 48.342471, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "grok-4.20-multi-agent-beta-0309; 95% CI [1252.84769478, 1265.09117861]; votes 24543; rank 57", "score": 1258.969437, "normalized_score": 41.965648, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}], "performance_rank": 13}, {"model": {"canonical_id": "moonshotai/Kimi-K3", "name": "Kimi-K3", "organization": {"slug": "moonshotai", "name": "Moonshot AI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/641c1e77c3983aa9490f8121/X1yT2rsaIbR9cdYGEVu0X.jpeg"}, "family": {"slug": "kimi-k3", "name": "Kimi K3"}, "url": "/models/moonshotai/kimi-k3"}, "performance_score": 39.813, "efficiency_score": 5.6088, "efficiency_performance_score": 94.5081, "average_output_tokens": 17542.5, "benchmark_count": 5, "performance_scope": "arc-agi-1+arc-agi-2+livebench+lmarena-agent+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.4545, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "Kimi K3 (Max)", "score": 94.5, "normalized_score": 94.5, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "Kimi K3 (Max)", "score": 60.416667, "normalized_score": 60.416667, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "kimi-k3", "score": 81.019178, "normalized_score": 81.019178, "output_tokens_per_case": 13647.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-agent", "version": "agent-2026-10-16-a64ca3b12b6e", "configuration": "Kimi K3 (Max); 95% CI [1.20183745, 2.66737332]; sessions 135415; observations 12343129; rank 23", "score": 1.934605, "normalized_score": 50.967303, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/agent/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Kimi K3 (max)", "score": 82.23, "normalized_score": 82.23, "output_tokens_per_case": 21438.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 14, "efficiency_rank": 19}, {"model": {"canonical_id": "xai/grok-4.7", "name": "Grok 4.7", "organization": {"slug": "xai", "name": "xAI", "logo_url": "https://x.ai/favicon.ico"}, "family": {"slug": "grok-4", "name": "Grok 4"}, "url": "/models/xai/grok-4-7"}, "performance_score": 39.4513, "efficiency_score": 1.9657, "efficiency_performance_score": 93.6481, "average_output_tokens": 51370.0, "benchmark_count": 5, "performance_scope": "arc-agi-1+arc-agi-2+livebench+lmarena-agent+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.4545, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "Grok 4.7 (High)", "score": 90.166667, "normalized_score": 90.166667, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "Grok 4.7 (XHigh)", "score": 61.388889, "normalized_score": 61.388889, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "grok-4.7-xhigh", "score": 82.203353, "normalized_score": 82.203353, "output_tokens_per_case": 56776.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-agent", "version": "agent-2026-10-16-a64ca3b12b6e", "configuration": "Grok 4.7 (xHigh); 95% CI [1.57579589, 4.84117305]; sessions 15127; observations 2475030; rank 16", "score": 3.208484, "normalized_score": 51.604242, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/agent/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Grok 4.7 (high)", "score": 79.58, "normalized_score": 79.58, "output_tokens_per_case": 45964.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 15, "efficiency_rank": 32}, {"model": {"canonical_id": "Qwen/Qwen3.8-27B", "name": "Qwen3.8-27B", "organization": {"slug": "qwen", "name": "Qwen", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6215ca5692c0ecfba9186921/hrRM50-6XcdWgg2AKpENG.jpeg"}, "family": {"slug": "qwen3-8-27b", "name": "Qwen3 8 27b"}, "url": "/models/qwen/qwen3-8-27b"}, "performance_score": 37.8988, "efficiency_score": 1.2474, "efficiency_performance_score": 89.8721, "average_output_tokens": 28740.0, "benchmark_count": 5, "performance_scope": "arc-agi-1+arc-agi-2+livebench+lmarena-text+lmarena-vision", "efficiency_scope": "livebench", "efficiency_benchmark_count": 1, "coverage": 0.4545, "efficiency_coverage": 0.3333, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "Qwen3.8-27B (XHigh)", "score": 87.5, "normalized_score": 87.5, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "Qwen3.8-27B (XHigh)", "score": 42.361111, "normalized_score": 42.361111, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "qwen3.8-27b", "score": 78.024105, "normalized_score": 78.024105, "output_tokens_per_case": 28740.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "qwen3.8-27b; 95% CI [1435.47949951, 1445.61514077]; votes 23294; rank 75", "score": 1440.54732, "normalized_score": 48.018244, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "qwen3.8-27b; 95% CI [1262.99100972, 1279.79432635]; votes 7013; rank 42", "score": 1271.392668, "normalized_score": 42.379756, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}], "performance_rank": 16, "efficiency_rank": 35}, {"model": {"canonical_id": "google-deepmind/gemini-3.5-flash-lite", "name": "Gemini 3.5 Flash-Lite", "organization": {"slug": "google-deepmind", "name": "Google DeepMind", "logo_url": "https://storage.googleapis.com/gdm-deepmind-com-prod-public/icons/google_deepmind_48dp.svg"}, "family": {"slug": "gemini-3", "name": "Gemini 3"}, "url": "/models/google-deepmind/gemini-3-5-flash-lite"}, "performance_score": 37.2852, "efficiency_score": 26.6944, "efficiency_performance_score": 76.0322, "average_output_tokens": 6778.0, "benchmark_count": 6, "performance_scope": "arc-agi-1+arc-agi-2+livebench+lmarena-text+lmarena-vision+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.5455, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "Gemini 3.5 Flash-Lite (High)", "score": 53.5, "normalized_score": 53.5, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "Gemini 3.5 Flash-Lite (High)", "score": 10.277778, "normalized_score": 10.277778, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "gemini-3.5-flash-lite-high", "score": 66.346626, "normalized_score": 66.346626, "output_tokens_per_case": 11526.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "gemini-3.5-flash-lite; 95% CI [1430.05687105, 1438.97565121]; votes 35851; rank 89", "score": 1434.516261, "normalized_score": 47.817209, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "gemini-3.5-flash-lite; 95% CI [1260.07450401, 1276.22711331]; votes 8381; rank 45", "score": 1268.150809, "normalized_score": 42.271694, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Gemini 3.5 Flash-Lite (minimal thinking)", "score": 65.0, "normalized_score": 65.0, "output_tokens_per_case": 2030.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 17, "efficiency_rank": 6}, {"model": {"canonical_id": "zai-org/glm-5.3-flash", "name": "GLM-5.3-Flash", "organization": {"slug": "zai-org", "name": "Z.ai", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/62dc173789b4cf157d36ebee/i_pxzM2ZDo3Ub-BEgIkE9.png"}, "family": {"slug": "glm-5-3-flash", "name": "Glm 5 3 Flash"}, "url": "/models/zai-org/glm-5-3-flash"}, "performance_score": 34.2815, "efficiency_score": 2.4949, "efficiency_performance_score": 89.8071, "average_output_tokens": 37504.0, "benchmark_count": 4, "performance_scope": "livebench+lmarena-text+lmarena-vision+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.3636, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "glm-5.3-flash", "score": 73.270866, "normalized_score": 73.270866, "output_tokens_per_case": 34707.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "glm-5.3-flash; 95% CI [1465.67476412, 1475.38456118]; votes 32925; rank 29", "score": 1470.529663, "normalized_score": 49.017655, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "glm-5.3-flash; 95% CI [1288.97978191, 1303.07121064]; votes 11157; rank 23", "score": 1296.025496, "normalized_score": 43.20085, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "GLM-5.3 Flash (max)", "score": 81.82, "normalized_score": 81.82, "output_tokens_per_case": 40301.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 18, "efficiency_rank": 29}, {"model": {"canonical_id": "deepseek-ai/DeepSeek-V4.1-Flash", "name": "DeepSeek-V4.1-Flash", "organization": {"slug": "deepseek-ai", "name": "DeepSeek", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6538815d1bdb3c40db94fbfa/xMBly9PUMphrFVMxLX4kq.png"}, "family": {"slug": "deepseek-v4-1", "name": "Deepseek V4 1"}, "url": "/models/deepseek-ai/deepseek-v4-1-flash"}, "performance_score": 32.9841, "efficiency_score": 3.4848, "efficiency_performance_score": 95.0659, "average_output_tokens": 30683.5, "benchmark_count": 4, "performance_scope": "arc-agi-1+arc-agi-2+livebench+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.3636, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "DeepSeek V4.1 Flash (Max)", "score": 94.5, "normalized_score": 94.5, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "DeepSeek V4.1 Flash (Max)", "score": 72.916667, "normalized_score": 72.916667, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "deepseek-v4.1-flash-max", "score": 83.20017, "normalized_score": 83.20017, "output_tokens_per_case": 36355.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "DeepSeek V4.1 Flash (max)", "score": 81.03, "normalized_score": 81.03, "output_tokens_per_case": 25012.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 19, "efficiency_rank": 24}, {"model": {"canonical_id": "openai/gpt-5.4-mini", "name": "GPT-5.4 Mini", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-5-4", "name": "Gpt 5 4"}, "url": "/models/openai/gpt-5-4-mini"}, "performance_score": 32.2047, "efficiency_score": 0.6733, "efficiency_performance_score": 80.0885, "average_output_tokens": 47448.0, "benchmark_count": 5, "performance_scope": "arc-agi-1+arc-agi-2+livebench+lmarena-text+lmarena-vision", "efficiency_scope": "livebench", "efficiency_benchmark_count": 1, "coverage": 0.4545, "efficiency_coverage": 0.3333, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "GPT-5.4 Mini (XHigh)", "score": 63.67, "normalized_score": 63.67, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "GPT-5.4 Mini (XHigh)", "score": 18.9, "normalized_score": 18.9, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "gpt-5.4-mini-xhigh", "score": 69.530263, "normalized_score": 69.530263, "output_tokens_per_case": 47448.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "gpt-5.4-mini-high; 95% CI [1407.73358875, 1415.16901218]; votes 63449; rank 137", "score": 1411.4513, "normalized_score": 47.048377, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "gpt-5.4-mini-high; 95% CI [1238.81649273, 1251.21275945]; votes 25733; rank 68", "score": 1245.014626, "normalized_score": 41.500488, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}], "performance_rank": 20, "efficiency_rank": 37}, {"model": {"canonical_id": "openai/gpt-5.4-nano", "name": "GPT-5.4 Nano", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-5-4", "name": "Gpt 5 4"}, "url": "/models/openai/gpt-5-4-nano"}, "performance_score": 29.8379, "efficiency_score": 0.7489, "efficiency_performance_score": 86.6955, "average_output_tokens": 46179.0, "benchmark_count": 5, "performance_scope": "arc-agi-1+arc-agi-2+livebench+lmarena-text+lmarena-vision", "efficiency_scope": "livebench", "efficiency_benchmark_count": 1, "coverage": 0.4545, "efficiency_coverage": 0.3333, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "GPT-5.4 Nano (XHigh)", "score": 51.5, "normalized_score": 51.5, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "GPT-5.4 Nano (XHigh)", "score": 5.69, "normalized_score": 5.69, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "gpt-5.4-nano-xhigh", "score": 75.266301, "normalized_score": 75.266301, "output_tokens_per_case": 46179.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "gpt-5.4-nano-high; 95% CI [1368.25704083, 1375.76986498]; votes 62396; rank 182", "score": 1372.013453, "normalized_score": 45.733782, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "gpt-5.4-nano-high; 95% CI [1189.64874058, 1202.27965668]; votes 25650; rank 94", "score": 1195.964199, "normalized_score": 39.865473, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}], "performance_rank": 21, "efficiency_rank": 36}, {"model": {"canonical_id": "thinkingmachines/Inkling-Small", "name": "Inkling-Small", "organization": {"slug": "thinkingmachines", "name": "Thinking Machines Lab", "logo_url": "https://thinkingmachines.ai/images/apple-touch-icon.png"}, "family": {"slug": "inkling", "name": "Inkling"}, "url": "/models/thinkingmachines/inkling-small"}, "performance_score": 28.773, "efficiency_score": null, "efficiency_performance_score": null, "average_output_tokens": null, "benchmark_count": 4, "performance_scope": "arc-agi-1+arc-agi-2+lmarena-text+lmarena-vision", "efficiency_scope": null, "efficiency_benchmark_count": 0, "coverage": 0.3636, "efficiency_coverage": 0.0, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "Inkling Small (XHigh)", "score": 84.0, "normalized_score": 84.0, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "Inkling Small (XHigh)", "score": 40.138889, "normalized_score": 40.138889, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "Inkling Small; 95% CI [1407.97725962, 1417.26957820]; votes 32304; rank 135", "score": 1412.623419, "normalized_score": 47.087447, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "Inkling Small; 95% CI [1226.97211879, 1243.66134454]; votes 7472; rank 75", "score": 1235.316732, "normalized_score": 41.177224, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}], "performance_rank": 22}, {"model": {"canonical_id": "qwen/qwen3.7-plus", "name": "Qwen3.7-Plus", "organization": {"slug": "qwen", "name": "Qwen", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6215ca5692c0ecfba9186921/hrRM50-6XcdWgg2AKpENG.jpeg"}, "family": {"slug": "qwen3-7-plus", "name": "Qwen3 7 Plus"}, "url": "/models/qwen/qwen3-7-plus"}, "performance_score": 26.4178, "efficiency_score": null, "efficiency_performance_score": null, "average_output_tokens": null, "benchmark_count": 3, "performance_scope": "lmarena-document+lmarena-text+lmarena-vision", "efficiency_scope": null, "efficiency_benchmark_count": 0, "coverage": 0.2727, "efficiency_coverage": 0.0, "selected_runs": [{"benchmark": "lmarena-document", "version": "document-2026-09-13-a64ca3b12b6e", "configuration": "qwen3.7-plus; 95% CI [1435.12302267, 1453.16578005]; votes 4591; rank 30", "score": 1444.144401, "normalized_score": 48.138147, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/document/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "qwen3.7-plus; 95% CI [1450.26283424, 1458.90144791]; votes 42075; rank 46", "score": 1454.582141, "normalized_score": 48.486071, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "qwen3.7-plus; 95% CI [1272.29971328, 1285.84102976]; votes 13636; rank 37", "score": 1279.070372, "normalized_score": 42.635679, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}], "performance_rank": 23}, {"model": {"canonical_id": "google/gemma-4-31B-it", "name": "Gemma 4 31B", "organization": {"slug": "google-deepmind", "name": "Google DeepMind", "logo_url": "https://storage.googleapis.com/gdm-deepmind-com-prod-public/icons/google_deepmind_48dp.svg"}, "family": {"slug": "gemma-4", "name": "Gemma 4"}, "url": "/models/google-deepmind/gemma-4-31b-it"}, "performance_score": 26.2123, "efficiency_score": null, "efficiency_performance_score": null, "average_output_tokens": null, "benchmark_count": 3, "performance_scope": "lmarena-document+lmarena-text+lmarena-vision", "efficiency_scope": null, "efficiency_benchmark_count": 0, "coverage": 0.2727, "efficiency_coverage": 0.0, "selected_runs": [{"benchmark": "lmarena-document", "version": "document-2026-09-13-a64ca3b12b6e", "configuration": "gemma-4-31b; 95% CI [1416.71159012, 1432.31286462]; votes 12326; rank 35", "score": 1424.512227, "normalized_score": 47.483741, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/document/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "gemma-4-31b; 95% CI [1435.47112822, 1450.25595360]; votes 6147; rank 67", "score": 1442.863541, "normalized_score": 48.095451, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "gemma-4-31b; 95% CI [1271.07071523, 1282.52723839]; votes 39669; rank 38", "score": 1276.798977, "normalized_score": 42.559966, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}], "performance_rank": 24}, {"model": {"canonical_id": "zai-org/glm-5.3", "name": "GLM-5.3", "organization": {"slug": "zai-org", "name": "Z.ai", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/62dc173789b4cf157d36ebee/i_pxzM2ZDo3Ub-BEgIkE9.png"}, "family": {"slug": "glm-5-3", "name": "Glm 5 3"}, "url": "/models/zai-org/glm-5-3"}, "performance_score": 26.025, "efficiency_score": 1.8182, "efficiency_performance_score": 93.5225, "average_output_tokens": 56149.0, "benchmark_count": 3, "performance_scope": "livebench+lmarena-text+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.2727, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "glm-5.3", "score": 79.146315, "normalized_score": 79.146315, "output_tokens_per_case": 62090.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "glm-5.3-max; 95% CI [1466.26042381, 1476.65163576]; votes 22543; rank 27", "score": 1471.45603, "normalized_score": 49.048534, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "GLM-5.3 (max)", "score": 82.39, "normalized_score": 82.39, "output_tokens_per_case": 50208.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 25, "efficiency_rank": 33}, {"model": {"canonical_id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct", "name": "Llama-4-Maverick-17B-128E-Instruct", "organization": {"slug": "meta-llama", "name": "Meta", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/646cf8084eefb026fb8fd8bc/oCTqufkdTkjyGodsx1vo1.png"}, "family": {"slug": "llama-4-maverick-17b-128e-instruct", "name": "Llama 4 Maverick 17b 128e Instruct"}, "url": "/models/meta-llama/llama-4-maverick-17b-128e-instruct"}, "performance_score": 25.5547, "efficiency_score": 23.532, "efficiency_performance_score": 81.3802, "average_output_tokens": 2232.0, "benchmark_count": 4, "performance_scope": "aider-polyglot+lmarena-text+lmarena-vision+tonebench", "efficiency_scope": "tonebench", "efficiency_benchmark_count": 1, "coverage": 0.3636, "efficiency_coverage": 0.3333, "selected_runs": [{"benchmark": "aider-polyglot", "version": "polyglot-225-5dc9490bb35f", "configuration": "whole; aider 0.81.2.dev", "score": 15.555556, "normalized_score": 15.555556, "output_tokens_per_case": null, "source_url": "https://github.com/Aider-AI/aider/blob/5dc9490bb35f9729ef2c95d00a19ccd30c26339c/aider/website/_data/polyglot_leaderboard.yml", "token_source_url": null, "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "llama-4-maverick-17b-128e-instruct; 95% CI [1282.93484207, 1291.44351277]; votes 39450; rank 261", "score": 1287.189177, "normalized_score": 42.906306, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "llama-4-maverick-17b-128e-instruct; 95% CI [1132.58229133, 1150.67926500]; votes 6922; rank 120", "score": 1141.630778, "normalized_score": 38.054359, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Llama 4 Maverick (no thinking)", "score": 69.93, "normalized_score": 69.93, "output_tokens_per_case": 2232.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 26, "efficiency_rank": 8}, {"model": {"canonical_id": "deepseek-ai/DeepSeek-V4-Pro", "name": "DeepSeek-V4-Pro", "organization": {"slug": "deepseek-ai", "name": "DeepSeek", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6538815d1bdb3c40db94fbfa/xMBly9PUMphrFVMxLX4kq.png"}, "family": {"slug": "deepseek-v4-pro", "name": "Deepseek V4 Pro"}, "url": "/models/deepseek-ai/deepseek-v4-pro"}, "performance_score": 24.6674, "efficiency_score": 4.0696, "efficiency_performance_score": 86.7402, "average_output_tokens": 26469.0, "benchmark_count": 3, "performance_scope": "livebench+lmarena-text+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.2727, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "deepseek-v4-pro", "score": 76.786076, "normalized_score": 76.786076, "output_tokens_per_case": 35014.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "deepseek-v4-pro; 95% CI [1447.27741116, 1455.03943137]; votes 57594; rank 49", "score": 1451.158421, "normalized_score": 48.371947, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "DeepSeek V4 Pro (xhigh)", "score": 73.07, "normalized_score": 73.07, "output_tokens_per_case": 17924.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 27, "efficiency_rank": 21}, {"model": {"canonical_id": "meta-llama/Llama-4-Scout-17B-16E-Instruct", "name": "Llama-4-Scout-17B-16E-Instruct", "organization": {"slug": "meta-llama", "name": "Meta", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/646cf8084eefb026fb8fd8bc/oCTqufkdTkjyGodsx1vo1.png"}, "family": {"slug": "llama-4-scout-17b-16e-instruct", "name": "Llama 4 Scout 17b 16e Instruct"}, "url": "/models/meta-llama/llama-4-scout-17b-16e-instruct"}, "performance_score": 23.8603, "efficiency_score": 33.3333, "efficiency_performance_score": 43.7449, "average_output_tokens": 847.0, "benchmark_count": 4, "performance_scope": "bfcl+lmarena-text+lmarena-vision+tonebench", "efficiency_scope": "tonebench", "efficiency_benchmark_count": 1, "coverage": 0.3636, "efficiency_coverage": 0.3333, "selected_runs": [{"benchmark": "bfcl", "version": "v4-ede5081a24bc", "configuration": "Llama-4-Scout-17B-16E-Instruct (FC)", "score": 28.13, "normalized_score": 28.13, "output_tokens_per_case": null, "source_url": "https://gorilla.cs.berkeley.edu/data_overall.csv", "token_source_url": null, "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "llama-4-scout-17b-16e-instruct; 95% CI [1274.44779094, 1283.86814615]; votes 29826; rank 273", "score": 1279.157969, "normalized_score": 42.638599, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "llama-4-scout-17b-16e-instruct; 95% CI [1108.78959993, 1127.66568063]; votes 6451; rank 127", "score": 1118.22764, "normalized_score": 37.274255, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Llama 4 Scout (no thinking)", "score": 37.59, "normalized_score": 37.59, "output_tokens_per_case": 847.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 28, "efficiency_rank": 3}, {"model": {"canonical_id": "openai/gpt-4o", "name": "GPT-4o", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-4o", "name": "Gpt 4o"}, "url": "/models/openai/gpt-4o"}, "performance_score": 23.7642, "efficiency_score": 31.8757, "efficiency_performance_score": 55.0681, "average_output_tokens": 1115.0, "benchmark_count": 4, "performance_scope": "aider-polyglot+lmarena-text+lmarena-vision+tonebench", "efficiency_scope": "tonebench", "efficiency_benchmark_count": 1, "coverage": 0.3636, "efficiency_coverage": 0.3333, "selected_runs": [{"benchmark": "aider-polyglot", "version": "polyglot-225-5dc9490bb35f", "configuration": "diff; aider 0.70.1.dev", "score": 23.111111, "normalized_score": 23.111111, "output_tokens_per_case": null, "source_url": "https://github.com/Aider-AI/aider/blob/5dc9490bb35f9729ef2c95d00a19ccd30c26339c/aider/website/_data/polyglot_leaderboard.yml", "token_source_url": null, "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "gpt-4o-2024-08-06; 95% CI [1278.31275237, 1286.69364786]; votes 45499; rank 267", "score": 1282.5032, "normalized_score": 42.750107, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "gpt-4o-2024-08-06; 95% CI [1052.04133780, 1077.00060680]; votes 3376; rank 136", "score": 1064.520972, "normalized_score": 35.484032, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "GPT-4o (no thinking)", "score": 47.32, "normalized_score": 47.32, "output_tokens_per_case": 1115.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 29, "efficiency_rank": 4}, {"model": {"canonical_id": "mistralai/mistral-large-2512", "name": "Mistral Large 3", "organization": {"slug": "mistralai", "name": "Mistral AI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/634c17653d11eaedd88b314d/9OgyfKstSZtbmsmuG8MbU.png"}, "family": {"slug": "mistral-large-3", "name": "Mistral Large 3"}, "url": "/models/mistralai/mistral-large-2512"}, "performance_score": 23.7101, "efficiency_score": 22.8469, "efficiency_performance_score": 71.8957, "average_output_tokens": 2031.0, "benchmark_count": 3, "performance_scope": "lmarena-text+lmarena-vision+tonebench", "efficiency_scope": "tonebench", "efficiency_benchmark_count": 1, "coverage": 0.2727, "efficiency_coverage": 0.3333, "selected_runs": [{"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "mistral-large-3; 95% CI [1425.33671505, 1430.99053174]; votes 84205; rank 98", "score": 1428.163623, "normalized_score": 47.605454, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "mistral-large-3; 95% CI [1212.81813492, 1228.69335345]; votes 8643; rank 83", "score": 1220.755744, "normalized_score": 40.691858, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Mistral Large 3 (no thinking)", "score": 61.78, "normalized_score": 61.78, "output_tokens_per_case": 2031.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 30, "efficiency_rank": 9}, {"model": {"canonical_id": "coherelabs/command-a-03-2025", "name": "Command A", "organization": {"slug": "coherelabs", "name": "Cohere", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678549441248-5e70f6048ce3c604d78fe133.png"}, "family": {"slug": "command-a", "name": "Command A"}, "url": "/models/coherelabs/command-a-03-2025"}, "performance_score": 22.4169, "efficiency_score": 31.7566, "efficiency_performance_score": 57.8145, "average_output_tokens": 1175.0, "benchmark_count": 4, "performance_scope": "aider-polyglot+bfcl+lmarena-text+tonebench", "efficiency_scope": "tonebench", "efficiency_benchmark_count": 1, "coverage": 0.3636, "efficiency_coverage": 0.3333, "selected_runs": [{"benchmark": "aider-polyglot", "version": "polyglot-225-5dc9490bb35f", "configuration": "whole; aider 0.77.1.dev", "score": 12.0, "normalized_score": 12.0, "output_tokens_per_case": null, "source_url": "https://github.com/Aider-AI/aider/blob/5dc9490bb35f9729ef2c95d00a19ccd30c26339c/aider/website/_data/polyglot_leaderboard.yml", "token_source_url": null, "verification_status": "verified_recomputed"}, {"benchmark": "bfcl", "version": "v4-ede5081a24bc", "configuration": "Command A (FC)", "score": 46.49, "normalized_score": 46.49, "output_tokens_per_case": null, "source_url": "https://gorilla.cs.berkeley.edu/data_overall.csv", "token_source_url": null, "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "command-a-03-2025; 95% CI [1327.49064818, 1334.38717569]; votes 55766; rank 225", "score": 1330.938912, "normalized_score": 44.36463, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Cohere Command A (03-2025) (no thinking)", "score": 49.68, "normalized_score": 49.68, "output_tokens_per_case": 1175.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 31, "efficiency_rank": 5}, {"model": {"canonical_id": "anthropic/claude-haiku-4-5", "name": "Claude Haiku 4.5", "organization": {"slug": "anthropic", "name": "Anthropic", "logo_url": "https://platform.claude.com/favicon.ico"}, "family": {"slug": "claude-4-5", "name": "Claude 4 5"}, "url": "/models/anthropic/claude-haiku-4-5"}, "performance_score": 21.8818, "efficiency_score": null, "efficiency_performance_score": null, "average_output_tokens": null, "benchmark_count": 4, "performance_scope": "arc-agi-1+arc-agi-2+lmarena-document+lmarena-text", "efficiency_scope": null, "efficiency_benchmark_count": 0, "coverage": 0.3636, "efficiency_coverage": 0.0, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "Claude Haiku 4.5 (Thinking 32K)", "score": 47.67, "normalized_score": 47.67, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "Claude Haiku 4.5 (Thinking 32K)", "score": 4.03, "normalized_score": 4.03, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-document", "version": "document-2026-09-13-a64ca3b12b6e", "configuration": "claude-haiku-4-5-20251001; 95% CI [1414.09579972, 1425.83505080]; votes 34677; rank 37", "score": 1419.965425, "normalized_score": 47.332181, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/document/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "claude-haiku-4-5-20251001; 95% CI [1394.24930739, 1399.03971640]; votes 149199; rank 159", "score": 1396.644512, "normalized_score": 46.554817, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}], "performance_rank": 32}, {"model": {"canonical_id": "openai/gpt-oss-120b", "name": "gpt-oss-120b", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-oss-120b", "name": "Gpt Oss 120b"}, "url": "/models/openai/gpt-oss-120b"}, "performance_score": 21.2807, "efficiency_score": 15.2102, "efficiency_performance_score": 71.0011, "average_output_tokens": 6327.82, "benchmark_count": 3, "performance_scope": "aider-polyglot+lmarena-text+tonebench", "efficiency_scope": "aider-polyglot+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.2727, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "aider-polyglot", "version": "polyglot-225-5dc9490bb35f", "configuration": "diff; aider 0.85.3.dev", "score": 41.777778, "normalized_score": 41.777778, "output_tokens_per_case": 3806.64, "source_url": "https://github.com/Aider-AI/aider/blob/5dc9490bb35f9729ef2c95d00a19ccd30c26339c/aider/website/_data/polyglot_leaderboard.yml", "token_source_url": "https://github.com/Aider-AI/aider/blob/5dc9490bb35f9729ef2c95d00a19ccd30c26339c/aider/website/_data/polyglot_leaderboard.yml", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "gpt-oss-120b; 95% CI [1361.16495776, 1369.85717870]; votes 30206; rank 192", "score": 1365.511068, "normalized_score": 45.517036, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "gpt-oss 120B (high)", "score": 61.29, "normalized_score": 61.29, "output_tokens_per_case": 8849.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 33, "efficiency_rank": 13}, {"model": {"canonical_id": "openai/gpt-4o-mini", "name": "GPT-4o Mini", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-4o", "name": "Gpt 4o"}, "url": "/models/openai/gpt-4o-mini"}, "performance_score": 20.7485, "efficiency_score": 26.3357, "efficiency_performance_score": 54.6375, "average_output_tokens": 1339.0, "benchmark_count": 4, "performance_scope": "aider-polyglot+lmarena-text+lmarena-vision+tonebench", "efficiency_scope": "tonebench", "efficiency_benchmark_count": 1, "coverage": 0.3636, "efficiency_coverage": 0.3333, "selected_runs": [{"benchmark": "aider-polyglot", "version": "polyglot-225-5dc9490bb35f", "configuration": "whole; aider 0.69.2.dev", "score": 3.555556, "normalized_score": 3.555556, "output_tokens_per_case": null, "source_url": "https://github.com/Aider-AI/aider/blob/5dc9490bb35f9729ef2c95d00a19ccd30c26339c/aider/website/_data/polyglot_leaderboard.yml", "token_source_url": null, "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "gpt-4o-mini-2024-07-18; 95% CI [1282.82219462, 1289.86344250]; votes 68705; rank 263", "score": 1286.342819, "normalized_score": 42.878094, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "gpt-4o-mini-2024-07-18; 95% CI [1057.29887437, 1073.89816601]; votes 17341; rank 135", "score": 1065.59852, "normalized_score": 35.519951, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "GPT-4o mini (no thinking)", "score": 46.95, "normalized_score": 46.95, "output_tokens_per_case": 1339.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 34, "efficiency_rank": 7}, {"model": {"canonical_id": "moonshotai/Kimi-K2-Instruct", "name": "Kimi-K2-Instruct", "organization": {"slug": "moonshotai", "name": "Moonshot AI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/641c1e77c3983aa9490f8121/X1yT2rsaIbR9cdYGEVu0X.jpeg"}, "family": {"slug": "kimi-k2-instruct", "name": "Kimi K2 Instruct"}, "url": "/models/moonshotai/kimi-k2-instruct"}, "performance_score": 18.1818, "efficiency_score": 33.3333, "efficiency_performance_score": 100.0, "average_output_tokens": 1617.09, "benchmark_count": 2, "performance_scope": "aider-polyglot+bfcl", "efficiency_scope": "aider-polyglot", "efficiency_benchmark_count": 1, "coverage": 0.1818, "efficiency_coverage": 0.3333, "selected_runs": [{"benchmark": "aider-polyglot", "version": "polyglot-225-5dc9490bb35f", "configuration": "diff; aider 0.85.3.dev", "score": 59.111111, "normalized_score": 59.111111, "output_tokens_per_case": 1617.09, "source_url": "https://github.com/Aider-AI/aider/blob/5dc9490bb35f9729ef2c95d00a19ccd30c26339c/aider/website/_data/polyglot_leaderboard.yml", "token_source_url": "https://github.com/Aider-AI/aider/blob/5dc9490bb35f9729ef2c95d00a19ccd30c26339c/aider/website/_data/polyglot_leaderboard.yml", "verification_status": "verified_recomputed"}, {"benchmark": "bfcl", "version": "v4-ede5081a24bc", "configuration": "Moonshotai-Kimi-K2-Instruct (FC)", "score": 59.06, "normalized_score": 59.06, "output_tokens_per_case": null, "source_url": "https://gorilla.cs.berkeley.edu/data_overall.csv", "token_source_url": null, "verification_status": "verified_recomputed"}], "performance_rank": 35, "efficiency_rank": 1}, {"model": {"canonical_id": "baidu/ernie-5.1", "name": "ERNIE 5.1", "organization": {"slug": "baidu", "name": "Baidu", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/64f187a2cc1c03340ac30498/TYYUxK8xD1AxExFMWqbZD.png"}, "family": {"slug": "ernie-5", "name": "Ernie 5"}, "url": "/models/baidu/ernie-5-1"}, "performance_score": 17.8412, "efficiency_score": null, "efficiency_performance_score": null, "average_output_tokens": null, "benchmark_count": 2, "performance_scope": "lmarena-search+lmarena-text", "efficiency_scope": null, "efficiency_benchmark_count": 0, "coverage": 0.1818, "efficiency_coverage": 0.0, "selected_runs": [{"benchmark": "lmarena-search", "version": "search-2026-10-13-a64ca3b12b6e", "configuration": "ernie-5.1; 95% CI [1217.24341628, 1236.18668968]; votes 4024; rank 11", "score": 1226.715053, "normalized_score": 40.890502, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/search/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "ernie-5.1; 95% CI [1463.22136313, 1472.23707800]; votes 39468; rank 34", "score": 1467.729221, "normalized_score": 48.924307, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}], "performance_rank": 36}, {"model": {"canonical_id": "Qwen/Qwen3.5-397B-A17B", "name": "Qwen3.5-397B-A17B", "organization": {"slug": "qwen", "name": "Qwen", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6215ca5692c0ecfba9186921/hrRM50-6XcdWgg2AKpENG.jpeg"}, "family": {"slug": "qwen3-5-397b-a17b", "name": "Qwen3 5 397b A17b"}, "url": "/models/qwen/qwen3-5-397b-a17b"}, "performance_score": 17.5207, "efficiency_score": null, "efficiency_performance_score": null, "average_output_tokens": null, "benchmark_count": 2, "performance_scope": "lmarena-text+lmarena-vision", "efficiency_scope": null, "efficiency_benchmark_count": 0, "coverage": 0.1818, "efficiency_coverage": 0.0, "selected_runs": [{"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "qwen3.5-397b-a17b; 95% CI [1434.65086689, 1440.78699055]; votes 93567; rank 81", "score": 1437.718929, "normalized_score": 47.923964, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "qwen3.5-397b-a17b; 95% CI [1257.19517602, 1267.83577721]; votes 32058; rank 54", "score": 1262.515477, "normalized_score": 42.083849, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}], "performance_rank": 37}, {"model": {"canonical_id": "google/gemma-4-26B-A4B-it", "name": "Gemma 4 26B-A4B", "organization": {"slug": "google-deepmind", "name": "Google DeepMind", "logo_url": "https://storage.googleapis.com/gdm-deepmind-com-prod-public/icons/google_deepmind_48dp.svg"}, "family": {"slug": "gemma-4", "name": "Gemma 4"}, "url": "/models/google-deepmind/gemma-4-26b-a4b-it"}, "performance_score": 17.4792, "efficiency_score": null, "efficiency_performance_score": null, "average_output_tokens": null, "benchmark_count": 2, "performance_scope": "lmarena-text+lmarena-vision", "efficiency_scope": null, "efficiency_benchmark_count": 0, "coverage": 0.1818, "efficiency_coverage": 0.0, "selected_runs": [{"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "gemma-4-26b-a4b; 95% CI [1426.70039347, 1441.53160125]; votes 6094; rank 90", "score": 1434.115997, "normalized_score": 47.803867, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "gemma-4-26b-a4b; 95% CI [1253.23971386, 1266.15382555]; votes 23943; rank 55", "score": 1259.69677, "normalized_score": 41.989892, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}], "performance_rank": 38}, {"model": {"canonical_id": "openai/gpt-5.5-pro", "name": "GPT-5.5 Pro", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-5-5", "name": "Gpt 5 5"}, "url": "/models/openai/gpt-5-5-pro"}, "performance_score": 17.0001, "efficiency_score": null, "efficiency_performance_score": null, "average_output_tokens": null, "benchmark_count": 2, "performance_scope": "arc-agi-1+arc-agi-2", "efficiency_scope": null, "efficiency_benchmark_count": 0, "coverage": 0.1818, "efficiency_coverage": 0.0, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "GPT-5.5 Pro (High)", "score": 96.5, "normalized_score": 96.5, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "GPT-5.5 Pro (High)", "score": 84.58, "normalized_score": 84.58, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}], "performance_rank": 39}, {"model": {"canonical_id": "tencent/Hy3", "name": "Hy3", "organization": {"slug": "tencent", "name": "Tencent", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/5dd96eb166059660ed1ee413/Lp3m-XLpjQGwBItlvn69q.png"}, "family": {"slug": "hy3", "name": "Hy3"}, "url": "/models/tencent/hy3"}, "performance_score": 16.3097, "efficiency_score": null, "efficiency_performance_score": null, "average_output_tokens": null, "benchmark_count": 2, "performance_scope": "lmarena-agent+lmarena-text", "efficiency_scope": null, "efficiency_benchmark_count": 0, "coverage": 0.1818, "efficiency_coverage": 0.0, "selected_runs": [{"benchmark": "lmarena-agent", "version": "agent-2026-10-16-a64ca3b12b6e", "configuration": "Hy3; 95% CI [-7.50774599, -4.49280945]; sessions 31296; observations 1149668; rank 41", "score": -6.000278, "normalized_score": 46.999861, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/agent/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "hy3; 95% CI [1431.86907820, 1444.13361939]; votes 12208; rank 80", "score": 1438.001349, "normalized_score": 47.933378, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}], "performance_rank": 40}, {"model": {"canonical_id": "qwen/qwen3.8-flash", "name": "Qwen3.8-Flash", "organization": {"slug": "qwen", "name": "Qwen", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6215ca5692c0ecfba9186921/hrRM50-6XcdWgg2AKpENG.jpeg"}, "family": {"slug": "qwen3-8-flash", "name": "Qwen3 8 Flash"}, "url": "/models/qwen/qwen3-8-flash"}, "performance_score": 16.2513, "efficiency_score": 2.4581, "efficiency_performance_score": 89.3821, "average_output_tokens": 43014.0, "benchmark_count": 2, "performance_scope": "livebench+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.1818, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "qwen3.8-flash-next", "score": 79.120246, "normalized_score": 79.120246, "output_tokens_per_case": 54438.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Qwen3.8 Flash (thinking on)", "score": 75.3, "normalized_score": 75.3, "output_tokens_per_case": 31590.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 41, "efficiency_rank": 30}, {"model": {"canonical_id": "upstage/solar-pro-4", "name": "Solar Pro 4", "organization": {"slug": "upstage", "name": "Upstage", "logo_url": "https://cdn.prod.website-files.com/6743d5190bb2b52f38e99e37/6743f495cc3c0ed693e0b5f3_Logo_Black.avif"}, "family": {"slug": "solar-pro", "name": "Solar Pro"}, "url": "/models/upstage/solar-pro-4"}, "performance_score": 14.8746, "efficiency_score": null, "efficiency_performance_score": null, "average_output_tokens": null, "benchmark_count": 2, "performance_scope": "lmarena-agent+lmarena-text", "efficiency_scope": null, "efficiency_benchmark_count": 0, "coverage": 0.1818, "efficiency_coverage": 0.0, "selected_runs": [{"benchmark": "lmarena-agent", "version": "agent-2026-10-16-a64ca3b12b6e", "configuration": "Solar Pro 4; 95% CI [-22.42702213, -17.68944380]; sessions 10243; observations 452978; rank 52", "score": -20.058233, "normalized_score": 39.970884, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/agent/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "solar-pro4; 95% CI [1381.43817825, 1392.00326711]; votes 21281; rank 169", "score": 1386.720723, "normalized_score": 46.224024, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}], "performance_rank": 42}, {"model": {"canonical_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", "name": "NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", "organization": {"slug": "nvidia", "name": "NVIDIA", "logo_url": "https://www.nvidia.com/etc/designs/nvidiaGDC/clientlibs_base/images/NVIDIA-Logo.svg"}, "family": {"slug": "nvidia-nemotron-3-ultra-550b-a55b-bf16", "name": "Nvidia Nemotron 3 Ultra 550b A55b Bf16"}, "url": "/models/nvidia/nvidia-nemotron-3-ultra-550b-a55b-bf16"}, "performance_score": 14.7479, "efficiency_score": 19.3199, "efficiency_performance_score": 81.1133, "average_output_tokens": 22179.5, "benchmark_count": 2, "performance_scope": "livebench+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.1818, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "nemotron-3-ultra-550b-a55b", "score": 73.491995, "normalized_score": 73.491995, "output_tokens_per_case": 41654.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Nemotron 3 Ultra 550B (high)", "score": 66.66, "normalized_score": 66.66, "output_tokens_per_case": 2705.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 43, "efficiency_rank": 11}, {"model": {"canonical_id": "amazon/nova-2-lite-v1:0", "name": "Nova 2 Lite", "organization": {"slug": "amazon", "name": "Amazon", "logo_url": "https://aws.amazon.com/favicon.ico"}, "family": {"slug": "nova-2", "name": "Nova 2"}, "url": "/models/amazon/nova-2-lite-v1-0"}, "performance_score": 12.5202, "efficiency_score": null, "efficiency_performance_score": null, "average_output_tokens": null, "benchmark_count": 2, "performance_scope": "bfcl+lmarena-text", "efficiency_scope": null, "efficiency_benchmark_count": 0, "coverage": 0.1818, "efficiency_coverage": 0.0, "selected_runs": [{"benchmark": "bfcl", "version": "v4-ede5081a24bc", "configuration": "Amazon-Nova-2-Lite-v1:0 (FC)", "score": 27.1, "normalized_score": 27.1, "output_tokens_per_case": null, "source_url": "https://gorilla.cs.berkeley.edu/data_overall.csv", "token_source_url": null, "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "nova-2-lite; 95% CI [1355.81915120, 1367.83207069]; votes 12413; rank 195", "score": 1361.825611, "normalized_score": 45.394187, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}], "performance_rank": 44}, {"model": {"canonical_id": "microsoft/phi-4", "name": "phi-4", "organization": {"slug": "microsoft", "name": "Microsoft", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/1583646260758-5e64858c87403103f9f1055d.png"}, "family": {"slug": "phi-4", "name": "Phi 4"}, "url": "/models/microsoft/phi-4"}, "performance_score": 11.8904, "efficiency_score": null, "efficiency_performance_score": null, "average_output_tokens": null, "benchmark_count": 2, "performance_scope": "bfcl+lmarena-text", "efficiency_scope": null, "efficiency_benchmark_count": 0, "coverage": 0.1818, "efficiency_coverage": 0.0, "selected_runs": [{"benchmark": "bfcl", "version": "v4-ede5081a24bc", "configuration": "Phi-4 (Prompt)", "score": 28.79, "normalized_score": 28.79, "output_tokens_per_case": null, "source_url": "https://gorilla.cs.berkeley.edu/data_overall.csv", "token_source_url": null, "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "phi-4; 95% CI [1212.07369450, 1221.23689100]; votes 24126; rank 314", "score": 1216.655293, "normalized_score": 40.555176, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}], "performance_rank": 45}, {"model": {"canonical_id": "google-deepmind/gemini-2.5-flash-lite", "name": "Gemini 2.5 Flash-Lite", "organization": {"slug": "google-deepmind", "name": "Google DeepMind", "logo_url": "https://storage.googleapis.com/gdm-deepmind-com-prod-public/icons/google_deepmind_48dp.svg"}, "family": {"slug": "gemini-2-5", "name": "Gemini 2 5"}, "url": "/models/google-deepmind/gemini-2-5-flash-lite"}, "performance_score": 10.7352, "efficiency_score": 19.2011, "efficiency_performance_score": 70.6273, "average_output_tokens": 2374.0, "benchmark_count": 2, "performance_scope": "bfcl+tonebench", "efficiency_scope": "tonebench", "efficiency_benchmark_count": 1, "coverage": 0.1818, "efficiency_coverage": 0.3333, "selected_runs": [{"benchmark": "bfcl", "version": "v4-ede5081a24bc", "configuration": "Gemini-2.5-Flash-Lite (Prompt)", "score": 28.03, "normalized_score": 28.03, "output_tokens_per_case": null, "source_url": "https://gorilla.cs.berkeley.edu/data_overall.csv", "token_source_url": null, "verification_status": "verified_recomputed"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Gemini 2.5 Flash-Lite (no thinking)", "score": 60.69, "normalized_score": 60.69, "output_tokens_per_case": 2374.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 46, "efficiency_rank": 12}, {"model": {"canonical_id": "Qwen/Qwen3.5-35B-A3B", "name": "Qwen3.5-35B-A3B", "organization": {"slug": "qwen", "name": "Qwen", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6215ca5692c0ecfba9186921/hrRM50-6XcdWgg2AKpENG.jpeg"}, "family": {"slug": "qwen3-5-35b-a3b", "name": "Qwen3 5 35b A3b"}, "url": "/models/qwen/qwen3-5-35b-a3b"}, "performance_score": 8.5505, "efficiency_score": null, "efficiency_performance_score": null, "average_output_tokens": null, "benchmark_count": 1, "performance_scope": "lmarena-text", "efficiency_scope": null, "efficiency_benchmark_count": 0, "coverage": 0.0909, "efficiency_coverage": 0.0, "selected_runs": [{"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "qwen3.5-35b-a3b; 95% CI [1390.52780278, 1398.93686884]; votes 30457; rank 161", "score": 1394.732336, "normalized_score": 46.491078, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}], "performance_rank": 47}, {"model": {"canonical_id": "meta-models/Muse-Glimmer-30B", "name": "Muse Glimmer 30B", "organization": {"slug": "meta-models", "name": "Meta", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/646cf8084eefb026fb8fd8bc/oCTqufkdTkjyGodsx1vo1.png"}, "family": {"slug": "muse-glimmer", "name": "Muse Glimmer"}, "url": "/models/meta-models/muse-glimmer-30b"}, "performance_score": 8.5148, "efficiency_score": null, "efficiency_performance_score": null, "average_output_tokens": null, "benchmark_count": 1, "performance_scope": "lmarena-text", "efficiency_scope": null, "efficiency_benchmark_count": 0, "coverage": 0.0909, "efficiency_coverage": 0.0, "selected_runs": [{"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "muse-glimmer; 95% CI [1379.26475817, 1398.55311930]; votes 3897; rank 167", "score": 1388.908939, "normalized_score": 46.296965, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}], "performance_rank": 48}, {"model": {"canonical_id": "deepseek-ai/DeepSeek-R1", "name": "DeepSeek-R1", "organization": {"slug": "deepseek-ai", "name": "DeepSeek", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6538815d1bdb3c40db94fbfa/xMBly9PUMphrFVMxLX4kq.png"}, "family": {"slug": "deepseek-r1", "name": "Deepseek R1"}, "url": "/models/deepseek-ai/deepseek-r1"}, "performance_score": 8.4152, "efficiency_score": null, "efficiency_performance_score": null, "average_output_tokens": null, "benchmark_count": 1, "performance_scope": "lmarena-text", "efficiency_scope": null, "efficiency_benchmark_count": 0, "coverage": 0.0909, "efficiency_coverage": 0.0, "selected_runs": [{"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "deepseek-r1; 95% CI [1367.80631687, 1377.49940563]; votes 18524; rank 181", "score": 1372.652861, "normalized_score": 45.755095, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}], "performance_rank": 49}, {"model": {"canonical_id": "ibm-granite/granite-4.2-30b", "name": "Granite 4.2 30B", "organization": {"slug": "ibm-granite", "name": "IBM", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/639bcaa2445b133a4e942436/CEW-OjXkRkDNmTxSu8Egh.png"}, "family": {"slug": "granite-4-2", "name": "Granite 4 2"}, "url": "/models/ibm-granite/granite-4-2-30b"}, "performance_score": 8.3462, "efficiency_score": null, "efficiency_performance_score": null, "average_output_tokens": null, "benchmark_count": 1, "performance_scope": "lmarena-text", "efficiency_scope": null, "efficiency_benchmark_count": 0, "coverage": 0.0909, "efficiency_coverage": 0.0, "selected_runs": [{"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "granite-4.2-30b; 95% CI [1350.97772869, 1371.83470317]; votes 3401; rank 196", "score": 1361.406216, "normalized_score": 45.380207, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}], "performance_rank": 50}, {"model": {"canonical_id": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16", "name": "NVIDIA-Nemotron-3-Nano-30B-A3B-BF16", "organization": {"slug": "nvidia", "name": "NVIDIA", "logo_url": "https://www.nvidia.com/etc/designs/nvidiaGDC/clientlibs_base/images/NVIDIA-Logo.svg"}, "family": {"slug": "nvidia-nemotron-3-nano-30b-a3b-bf16", "name": "Nvidia Nemotron 3 Nano 30b A3b Bf16"}, "url": "/models/nvidia/nvidia-nemotron-3-nano-30b-a3b-bf16"}, "performance_score": 8.2629, "efficiency_score": null, "efficiency_performance_score": null, "average_output_tokens": null, "benchmark_count": 1, "performance_scope": "lmarena-text", "efficiency_scope": null, "efficiency_benchmark_count": 0, "coverage": 0.0909, "efficiency_coverage": 0.0, "selected_runs": [{"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "nvidia-nemotron-3-nano-30b-a3b-bf16; 95% CI [1342.43511795, 1353.20837526]; votes 15770; rank 209", "score": 1347.821747, "normalized_score": 44.927392, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}], "performance_rank": 51}, {"model": {"canonical_id": "perplexity/sonar-reasoning-pro", "name": "Sonar Reasoning Pro", "organization": {"slug": "perplexity", "name": "Perplexity", "logo_url": "https://www.perplexity.ai/favicon.ico"}, "family": {"slug": "sonar", "name": "Sonar"}, "url": "/models/perplexity/sonar-reasoning-pro"}, "performance_score": 8.2109, "efficiency_score": null, "efficiency_performance_score": null, "average_output_tokens": null, "benchmark_count": 1, "performance_scope": "lmarena-search", "efficiency_scope": null, "efficiency_benchmark_count": 0, "coverage": 0.0909, "efficiency_coverage": 0.0, "selected_runs": [{"benchmark": "lmarena-search", "version": "search-2026-10-13-a64ca3b12b6e", "configuration": "ppl-sonar-reasoning-pro-high; 95% CI [1133.19180048, 1144.81939817]; votes 29439; rank 37", "score": 1139.005599, "normalized_score": 37.966853, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/search/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}], "performance_rank": 52}, {"model": {"canonical_id": "tencent/Hy4-preview", "name": "Hy4 preview", "organization": {"slug": "tencent", "name": "Tencent", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/5dd96eb166059660ed1ee413/Lp3m-XLpjQGwBItlvn69q.png"}, "family": {"slug": "hy4", "name": "Hy4"}, "url": "/models/tencent/hy4-preview"}, "performance_score": 8.1859, "efficiency_score": null, "efficiency_performance_score": null, "average_output_tokens": null, "benchmark_count": 1, "performance_scope": "lmarena-agent", "efficiency_scope": null, "efficiency_benchmark_count": 0, "coverage": 0.0909, "efficiency_coverage": 0.0, "selected_runs": [{"benchmark": "lmarena-agent", "version": "agent-2026-10-16-a64ca3b12b6e", "configuration": "Hy4 preview; 95% CI [2.00929922, 3.35139547]; sessions 84828; observations 8314177; rank 20", "score": 2.680347, "normalized_score": 51.340174, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/agent/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}], "performance_rank": 53}, {"model": {"canonical_id": "perplexity/sonar-pro", "name": "Sonar Pro", "organization": {"slug": "perplexity", "name": "Perplexity", "logo_url": "https://www.perplexity.ai/favicon.ico"}, "family": {"slug": "sonar", "name": "Sonar"}, "url": "/models/perplexity/sonar-pro"}, "performance_score": 8.148, "efficiency_score": null, "efficiency_performance_score": null, "average_output_tokens": null, "benchmark_count": 1, "performance_scope": "lmarena-search", "efficiency_scope": null, "efficiency_benchmark_count": 0, "coverage": 0.0909, "efficiency_coverage": 0.0, "selected_runs": [{"benchmark": "lmarena-search", "version": "search-2026-10-13-a64ca3b12b6e", "configuration": "ppl-sonar-pro-high; 95% CI [1124.47147876, 1136.08107434]; votes 28899; rank 39", "score": 1130.276277, "normalized_score": 37.675876, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/search/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}], "performance_rank": 54}, {"model": {"canonical_id": "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16", "name": "NVIDIA Nemotron 3.5 Lightning 30B-A3B", "organization": {"slug": "nvidia", "name": "NVIDIA", "logo_url": "https://www.nvidia.com/etc/designs/nvidiaGDC/clientlibs_base/images/NVIDIA-Logo.svg"}, "family": {"slug": "nvidia-nemotron-3-5-lightning", "name": "Nvidia Nemotron 3 5 Lightning"}, "url": "/models/nvidia/nvidia-nemotron-3-5-lightning-30b-a3b-bf16"}, "performance_score": 8.1468, "efficiency_score": null, "efficiency_performance_score": null, "average_output_tokens": null, "benchmark_count": 1, "performance_scope": "lmarena-text", "efficiency_scope": null, "efficiency_benchmark_count": 0, "coverage": 0.0909, "efficiency_coverage": 0.0, "selected_runs": [{"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "nvidia-nemotron-3.5-lightning-30b-a3b-nvfp4; 95% CI [1323.35291228, 1334.41299389]; votes 19938; rank 229", "score": 1328.882953, "normalized_score": 44.296098, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}], "performance_rank": 55}, {"model": {"canonical_id": "ibm-granite/granite-4.2-8b", "name": "Granite 4.2 8B", "organization": {"slug": "ibm-granite", "name": "IBM", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/639bcaa2445b133a4e942436/CEW-OjXkRkDNmTxSu8Egh.png"}, "family": {"slug": "granite-4-2", "name": "Granite 4 2"}, "url": "/models/ibm-granite/granite-4-2-8b"}, "performance_score": 8.0898, "efficiency_score": null, "efficiency_performance_score": null, "average_output_tokens": null, "benchmark_count": 1, "performance_scope": "lmarena-text", "efficiency_scope": null, "efficiency_benchmark_count": 0, "coverage": 0.0909, "efficiency_coverage": 0.0, "selected_runs": [{"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "granite-4.2-8b; 95% CI [1308.51127780, 1330.64584507]; votes 3254; rank 234", "score": 1319.578561, "normalized_score": 43.985952, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}], "performance_rank": 56}, {"model": {"canonical_id": "mistralai/mistral-large-4", "name": "Mistral Large 4", "organization": {"slug": "mistralai", "name": "Mistral AI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/634c17653d11eaedd88b314d/9OgyfKstSZtbmsmuG8MbU.png"}, "family": {"slug": "mistral-large-4", "name": "Mistral Large 4"}, "url": "/models/mistralai/mistral-large-4"}, "performance_score": 8.0286, "efficiency_score": 1.3708, "efficiency_performance_score": 88.3142, "average_output_tokens": 25699.0, "benchmark_count": 1, "performance_scope": "livebench", "efficiency_scope": "livebench", "efficiency_benchmark_count": 1, "coverage": 0.0909, "efficiency_coverage": 0.3333, "selected_runs": [{"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "mistral-large-4-high", "score": 76.671572, "normalized_score": 76.671572, "output_tokens_per_case": 25699.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}], "performance_rank": 57, "efficiency_rank": 34}, {"model": {"canonical_id": "allenai/Olmo-3-32B-Think", "name": "Olmo-3-32B-Think", "organization": {"slug": "allenai", "name": "Ai2", "logo_url": "https://allenai.org/icon.png"}, "family": {"slug": "olmo-3-32b-think", "name": "Olmo 3 32b Think"}, "url": "/models/allenai/olmo-3-32b-think"}, "performance_score": 7.9662, "efficiency_score": null, "efficiency_performance_score": null, "average_output_tokens": null, "benchmark_count": 1, "performance_scope": "lmarena-text", "efficiency_scope": null, "efficiency_benchmark_count": 0, "coverage": 0.0909, "efficiency_coverage": 0.0, "selected_runs": [{"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "olmo-3-32b-think; 95% CI [1291.17882644, 1307.65677276]; votes 5831; rank 248", "score": 1299.4178, "normalized_score": 43.313927, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}], "performance_rank": 58}, {"model": {"canonical_id": "ibm-granite/granite-4.2-3b", "name": "Granite 4.2 3B", "organization": {"slug": "ibm-granite", "name": "IBM", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/639bcaa2445b133a4e942436/CEW-OjXkRkDNmTxSu8Egh.png"}, "family": {"slug": "granite-4-2", "name": "Granite 4 2"}, "url": "/models/ibm-granite/granite-4-2-3b"}, "performance_score": 7.9265, "efficiency_score": null, "efficiency_performance_score": null, "average_output_tokens": null, "benchmark_count": 1, "performance_scope": "lmarena-text", "efficiency_scope": null, "efficiency_benchmark_count": 0, "coverage": 0.0909, "efficiency_coverage": 0.0, "selected_runs": [{"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "granite-4.2-3b; 95% CI [1281.43969143, 1304.43063080]; votes 3251; rank 253", "score": 1292.935161, "normalized_score": 43.097839, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}], "performance_rank": 59}, {"model": {"canonical_id": "openai/gpt-oss-20b", "name": "gpt-oss-20b", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-oss", "name": "Gpt Oss"}, "url": "/models/openai/gpt-oss-20b"}, "performance_score": 7.8927, "efficiency_score": null, "efficiency_performance_score": null, "average_output_tokens": null, "benchmark_count": 1, "performance_scope": "lmarena-text", "efficiency_scope": null, "efficiency_benchmark_count": 0, "coverage": 0.0909, "efficiency_coverage": 0.0, "selected_runs": [{"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "gpt-oss-20b; 95% CI [1281.03637900, 1293.81371199]; votes 10419; rank 260", "score": 1287.425045, "normalized_score": 42.914168, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}], "performance_rank": 60}, {"model": {"canonical_id": "moonshotai/Kimi-K2.7-Code", "name": "Kimi K2.7 Code", "organization": {"slug": "moonshotai", "name": "Moonshot AI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/641c1e77c3983aa9490f8121/X1yT2rsaIbR9cdYGEVu0X.jpeg"}, "family": {"slug": "kimi-k2-7", "name": "Kimi K2 7"}, "url": "/models/moonshotai/kimi-k2-7-code"}, "performance_score": 7.4815, "efficiency_score": 2.5239, "efficiency_performance_score": 82.2968, "average_output_tokens": 13007.0, "benchmark_count": 1, "performance_scope": "livebench", "efficiency_scope": "livebench", "efficiency_benchmark_count": 1, "coverage": 0.0909, "efficiency_coverage": 0.3333, "selected_runs": [{"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "kimi-k2.7-code", "score": 71.447447, "normalized_score": 71.447447, "output_tokens_per_case": 13007.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}], "performance_rank": 61, "efficiency_rank": 28}, {"model": {"canonical_id": "xai/grok-build-0.1", "name": "Grok Build 0.1", "organization": {"slug": "xai", "name": "xAI", "logo_url": "https://x.ai/favicon.ico"}, "family": {"slug": "grok-build", "name": "Grok Build"}, "url": "/models/xai/grok-build-0-1"}, "performance_score": 7.4446, "efficiency_score": 33.3333, "efficiency_performance_score": 81.8905, "average_output_tokens": 980.0, "benchmark_count": 1, "performance_scope": "livebench", "efficiency_scope": "livebench", "efficiency_benchmark_count": 1, "coverage": 0.0909, "efficiency_coverage": 0.3333, "selected_runs": [{"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "grok-build-0.1", "score": 71.094763, "normalized_score": 71.094763, "output_tokens_per_case": 980.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}], "performance_rank": 62, "efficiency_rank": 2}, {"model": {"canonical_id": "coherelabs/command-a-reasoning-08-2025", "name": "Command A Reasoning", "organization": {"slug": "coherelabs", "name": "Cohere", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678549441248-5e70f6048ce3c604d78fe133.png"}, "family": {"slug": "command-a", "name": "Command A"}, "url": "/models/coherelabs/command-a-reasoning-08-2025"}, "performance_score": 5.5785, "efficiency_score": 20.6706, "efficiency_performance_score": 61.3639, "average_output_tokens": 1916.0, "benchmark_count": 1, "performance_scope": "tonebench", "efficiency_scope": "tonebench", "efficiency_benchmark_count": 1, "coverage": 0.0909, "efficiency_coverage": 0.3333, "selected_runs": [{"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Cohere Command A Reasoning (thinking on)", "score": 52.73, "normalized_score": 52.73, "output_tokens_per_case": 1916.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 63, "efficiency_rank": 10}], "efficiency": [{"model": {"canonical_id": "moonshotai/Kimi-K2-Instruct", "name": "Kimi-K2-Instruct", "organization": {"slug": "moonshotai", "name": "Moonshot AI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/641c1e77c3983aa9490f8121/X1yT2rsaIbR9cdYGEVu0X.jpeg"}, "family": {"slug": "kimi-k2-instruct", "name": "Kimi K2 Instruct"}, "url": "/models/moonshotai/kimi-k2-instruct"}, "performance_score": 18.1818, "efficiency_score": 33.3333, "efficiency_performance_score": 100.0, "average_output_tokens": 1617.09, "benchmark_count": 2, "performance_scope": "aider-polyglot+bfcl", "efficiency_scope": "aider-polyglot", "efficiency_benchmark_count": 1, "coverage": 0.1818, "efficiency_coverage": 0.3333, "selected_runs": [{"benchmark": "aider-polyglot", "version": "polyglot-225-5dc9490bb35f", "configuration": "diff; aider 0.85.3.dev", "score": 59.111111, "normalized_score": 59.111111, "output_tokens_per_case": 1617.09, "source_url": "https://github.com/Aider-AI/aider/blob/5dc9490bb35f9729ef2c95d00a19ccd30c26339c/aider/website/_data/polyglot_leaderboard.yml", "token_source_url": "https://github.com/Aider-AI/aider/blob/5dc9490bb35f9729ef2c95d00a19ccd30c26339c/aider/website/_data/polyglot_leaderboard.yml", "verification_status": "verified_recomputed"}, {"benchmark": "bfcl", "version": "v4-ede5081a24bc", "configuration": "Moonshotai-Kimi-K2-Instruct (FC)", "score": 59.06, "normalized_score": 59.06, "output_tokens_per_case": null, "source_url": "https://gorilla.cs.berkeley.edu/data_overall.csv", "token_source_url": null, "verification_status": "verified_recomputed"}], "performance_rank": 35, "efficiency_rank": 1}, {"model": {"canonical_id": "xai/grok-build-0.1", "name": "Grok Build 0.1", "organization": {"slug": "xai", "name": "xAI", "logo_url": "https://x.ai/favicon.ico"}, "family": {"slug": "grok-build", "name": "Grok Build"}, "url": "/models/xai/grok-build-0-1"}, "performance_score": 7.4446, "efficiency_score": 33.3333, "efficiency_performance_score": 81.8905, "average_output_tokens": 980.0, "benchmark_count": 1, "performance_scope": "livebench", "efficiency_scope": "livebench", "efficiency_benchmark_count": 1, "coverage": 0.0909, "efficiency_coverage": 0.3333, "selected_runs": [{"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "grok-build-0.1", "score": 71.094763, "normalized_score": 71.094763, "output_tokens_per_case": 980.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}], "performance_rank": 62, "efficiency_rank": 2}, {"model": {"canonical_id": "meta-llama/Llama-4-Scout-17B-16E-Instruct", "name": "Llama-4-Scout-17B-16E-Instruct", "organization": {"slug": "meta-llama", "name": "Meta", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/646cf8084eefb026fb8fd8bc/oCTqufkdTkjyGodsx1vo1.png"}, "family": {"slug": "llama-4-scout-17b-16e-instruct", "name": "Llama 4 Scout 17b 16e Instruct"}, "url": "/models/meta-llama/llama-4-scout-17b-16e-instruct"}, "performance_score": 23.8603, "efficiency_score": 33.3333, "efficiency_performance_score": 43.7449, "average_output_tokens": 847.0, "benchmark_count": 4, "performance_scope": "bfcl+lmarena-text+lmarena-vision+tonebench", "efficiency_scope": "tonebench", "efficiency_benchmark_count": 1, "coverage": 0.3636, "efficiency_coverage": 0.3333, "selected_runs": [{"benchmark": "bfcl", "version": "v4-ede5081a24bc", "configuration": "Llama-4-Scout-17B-16E-Instruct (FC)", "score": 28.13, "normalized_score": 28.13, "output_tokens_per_case": null, "source_url": "https://gorilla.cs.berkeley.edu/data_overall.csv", "token_source_url": null, "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "llama-4-scout-17b-16e-instruct; 95% CI [1274.44779094, 1283.86814615]; votes 29826; rank 273", "score": 1279.157969, "normalized_score": 42.638599, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "llama-4-scout-17b-16e-instruct; 95% CI [1108.78959993, 1127.66568063]; votes 6451; rank 127", "score": 1118.22764, "normalized_score": 37.274255, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Llama 4 Scout (no thinking)", "score": 37.59, "normalized_score": 37.59, "output_tokens_per_case": 847.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 28, "efficiency_rank": 3}, {"model": {"canonical_id": "openai/gpt-4o", "name": "GPT-4o", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-4o", "name": "Gpt 4o"}, "url": "/models/openai/gpt-4o"}, "performance_score": 23.7642, "efficiency_score": 31.8757, "efficiency_performance_score": 55.0681, "average_output_tokens": 1115.0, "benchmark_count": 4, "performance_scope": "aider-polyglot+lmarena-text+lmarena-vision+tonebench", "efficiency_scope": "tonebench", "efficiency_benchmark_count": 1, "coverage": 0.3636, "efficiency_coverage": 0.3333, "selected_runs": [{"benchmark": "aider-polyglot", "version": "polyglot-225-5dc9490bb35f", "configuration": "diff; aider 0.70.1.dev", "score": 23.111111, "normalized_score": 23.111111, "output_tokens_per_case": null, "source_url": "https://github.com/Aider-AI/aider/blob/5dc9490bb35f9729ef2c95d00a19ccd30c26339c/aider/website/_data/polyglot_leaderboard.yml", "token_source_url": null, "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "gpt-4o-2024-08-06; 95% CI [1278.31275237, 1286.69364786]; votes 45499; rank 267", "score": 1282.5032, "normalized_score": 42.750107, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "gpt-4o-2024-08-06; 95% CI [1052.04133780, 1077.00060680]; votes 3376; rank 136", "score": 1064.520972, "normalized_score": 35.484032, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "GPT-4o (no thinking)", "score": 47.32, "normalized_score": 47.32, "output_tokens_per_case": 1115.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 29, "efficiency_rank": 4}, {"model": {"canonical_id": "coherelabs/command-a-03-2025", "name": "Command A", "organization": {"slug": "coherelabs", "name": "Cohere", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678549441248-5e70f6048ce3c604d78fe133.png"}, "family": {"slug": "command-a", "name": "Command A"}, "url": "/models/coherelabs/command-a-03-2025"}, "performance_score": 22.4169, "efficiency_score": 31.7566, "efficiency_performance_score": 57.8145, "average_output_tokens": 1175.0, "benchmark_count": 4, "performance_scope": "aider-polyglot+bfcl+lmarena-text+tonebench", "efficiency_scope": "tonebench", "efficiency_benchmark_count": 1, "coverage": 0.3636, "efficiency_coverage": 0.3333, "selected_runs": [{"benchmark": "aider-polyglot", "version": "polyglot-225-5dc9490bb35f", "configuration": "whole; aider 0.77.1.dev", "score": 12.0, "normalized_score": 12.0, "output_tokens_per_case": null, "source_url": "https://github.com/Aider-AI/aider/blob/5dc9490bb35f9729ef2c95d00a19ccd30c26339c/aider/website/_data/polyglot_leaderboard.yml", "token_source_url": null, "verification_status": "verified_recomputed"}, {"benchmark": "bfcl", "version": "v4-ede5081a24bc", "configuration": "Command A (FC)", "score": 46.49, "normalized_score": 46.49, "output_tokens_per_case": null, "source_url": "https://gorilla.cs.berkeley.edu/data_overall.csv", "token_source_url": null, "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "command-a-03-2025; 95% CI [1327.49064818, 1334.38717569]; votes 55766; rank 225", "score": 1330.938912, "normalized_score": 44.36463, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Cohere Command A (03-2025) (no thinking)", "score": 49.68, "normalized_score": 49.68, "output_tokens_per_case": 1175.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 31, "efficiency_rank": 5}, {"model": {"canonical_id": "google-deepmind/gemini-3.5-flash-lite", "name": "Gemini 3.5 Flash-Lite", "organization": {"slug": "google-deepmind", "name": "Google DeepMind", "logo_url": "https://storage.googleapis.com/gdm-deepmind-com-prod-public/icons/google_deepmind_48dp.svg"}, "family": {"slug": "gemini-3", "name": "Gemini 3"}, "url": "/models/google-deepmind/gemini-3-5-flash-lite"}, "performance_score": 37.2852, "efficiency_score": 26.6944, "efficiency_performance_score": 76.0322, "average_output_tokens": 6778.0, "benchmark_count": 6, "performance_scope": "arc-agi-1+arc-agi-2+livebench+lmarena-text+lmarena-vision+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.5455, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "Gemini 3.5 Flash-Lite (High)", "score": 53.5, "normalized_score": 53.5, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "Gemini 3.5 Flash-Lite (High)", "score": 10.277778, "normalized_score": 10.277778, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "gemini-3.5-flash-lite-high", "score": 66.346626, "normalized_score": 66.346626, "output_tokens_per_case": 11526.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "gemini-3.5-flash-lite; 95% CI [1430.05687105, 1438.97565121]; votes 35851; rank 89", "score": 1434.516261, "normalized_score": 47.817209, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "gemini-3.5-flash-lite; 95% CI [1260.07450401, 1276.22711331]; votes 8381; rank 45", "score": 1268.150809, "normalized_score": 42.271694, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Gemini 3.5 Flash-Lite (minimal thinking)", "score": 65.0, "normalized_score": 65.0, "output_tokens_per_case": 2030.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 17, "efficiency_rank": 6}, {"model": {"canonical_id": "openai/gpt-4o-mini", "name": "GPT-4o Mini", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-4o", "name": "Gpt 4o"}, "url": "/models/openai/gpt-4o-mini"}, "performance_score": 20.7485, "efficiency_score": 26.3357, "efficiency_performance_score": 54.6375, "average_output_tokens": 1339.0, "benchmark_count": 4, "performance_scope": "aider-polyglot+lmarena-text+lmarena-vision+tonebench", "efficiency_scope": "tonebench", "efficiency_benchmark_count": 1, "coverage": 0.3636, "efficiency_coverage": 0.3333, "selected_runs": [{"benchmark": "aider-polyglot", "version": "polyglot-225-5dc9490bb35f", "configuration": "whole; aider 0.69.2.dev", "score": 3.555556, "normalized_score": 3.555556, "output_tokens_per_case": null, "source_url": "https://github.com/Aider-AI/aider/blob/5dc9490bb35f9729ef2c95d00a19ccd30c26339c/aider/website/_data/polyglot_leaderboard.yml", "token_source_url": null, "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "gpt-4o-mini-2024-07-18; 95% CI [1282.82219462, 1289.86344250]; votes 68705; rank 263", "score": 1286.342819, "normalized_score": 42.878094, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "gpt-4o-mini-2024-07-18; 95% CI [1057.29887437, 1073.89816601]; votes 17341; rank 135", "score": 1065.59852, "normalized_score": 35.519951, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "GPT-4o mini (no thinking)", "score": 46.95, "normalized_score": 46.95, "output_tokens_per_case": 1339.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 34, "efficiency_rank": 7}, {"model": {"canonical_id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct", "name": "Llama-4-Maverick-17B-128E-Instruct", "organization": {"slug": "meta-llama", "name": "Meta", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/646cf8084eefb026fb8fd8bc/oCTqufkdTkjyGodsx1vo1.png"}, "family": {"slug": "llama-4-maverick-17b-128e-instruct", "name": "Llama 4 Maverick 17b 128e Instruct"}, "url": "/models/meta-llama/llama-4-maverick-17b-128e-instruct"}, "performance_score": 25.5547, "efficiency_score": 23.532, "efficiency_performance_score": 81.3802, "average_output_tokens": 2232.0, "benchmark_count": 4, "performance_scope": "aider-polyglot+lmarena-text+lmarena-vision+tonebench", "efficiency_scope": "tonebench", "efficiency_benchmark_count": 1, "coverage": 0.3636, "efficiency_coverage": 0.3333, "selected_runs": [{"benchmark": "aider-polyglot", "version": "polyglot-225-5dc9490bb35f", "configuration": "whole; aider 0.81.2.dev", "score": 15.555556, "normalized_score": 15.555556, "output_tokens_per_case": null, "source_url": "https://github.com/Aider-AI/aider/blob/5dc9490bb35f9729ef2c95d00a19ccd30c26339c/aider/website/_data/polyglot_leaderboard.yml", "token_source_url": null, "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "llama-4-maverick-17b-128e-instruct; 95% CI [1282.93484207, 1291.44351277]; votes 39450; rank 261", "score": 1287.189177, "normalized_score": 42.906306, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "llama-4-maverick-17b-128e-instruct; 95% CI [1132.58229133, 1150.67926500]; votes 6922; rank 120", "score": 1141.630778, "normalized_score": 38.054359, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Llama 4 Maverick (no thinking)", "score": 69.93, "normalized_score": 69.93, "output_tokens_per_case": 2232.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 26, "efficiency_rank": 8}, {"model": {"canonical_id": "mistralai/mistral-large-2512", "name": "Mistral Large 3", "organization": {"slug": "mistralai", "name": "Mistral AI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/634c17653d11eaedd88b314d/9OgyfKstSZtbmsmuG8MbU.png"}, "family": {"slug": "mistral-large-3", "name": "Mistral Large 3"}, "url": "/models/mistralai/mistral-large-2512"}, "performance_score": 23.7101, "efficiency_score": 22.8469, "efficiency_performance_score": 71.8957, "average_output_tokens": 2031.0, "benchmark_count": 3, "performance_scope": "lmarena-text+lmarena-vision+tonebench", "efficiency_scope": "tonebench", "efficiency_benchmark_count": 1, "coverage": 0.2727, "efficiency_coverage": 0.3333, "selected_runs": [{"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "mistral-large-3; 95% CI [1425.33671505, 1430.99053174]; votes 84205; rank 98", "score": 1428.163623, "normalized_score": 47.605454, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "mistral-large-3; 95% CI [1212.81813492, 1228.69335345]; votes 8643; rank 83", "score": 1220.755744, "normalized_score": 40.691858, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Mistral Large 3 (no thinking)", "score": 61.78, "normalized_score": 61.78, "output_tokens_per_case": 2031.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 30, "efficiency_rank": 9}, {"model": {"canonical_id": "coherelabs/command-a-reasoning-08-2025", "name": "Command A Reasoning", "organization": {"slug": "coherelabs", "name": "Cohere", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678549441248-5e70f6048ce3c604d78fe133.png"}, "family": {"slug": "command-a", "name": "Command A"}, "url": "/models/coherelabs/command-a-reasoning-08-2025"}, "performance_score": 5.5785, "efficiency_score": 20.6706, "efficiency_performance_score": 61.3639, "average_output_tokens": 1916.0, "benchmark_count": 1, "performance_scope": "tonebench", "efficiency_scope": "tonebench", "efficiency_benchmark_count": 1, "coverage": 0.0909, "efficiency_coverage": 0.3333, "selected_runs": [{"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Cohere Command A Reasoning (thinking on)", "score": 52.73, "normalized_score": 52.73, "output_tokens_per_case": 1916.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 63, "efficiency_rank": 10}, {"model": {"canonical_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", "name": "NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", "organization": {"slug": "nvidia", "name": "NVIDIA", "logo_url": "https://www.nvidia.com/etc/designs/nvidiaGDC/clientlibs_base/images/NVIDIA-Logo.svg"}, "family": {"slug": "nvidia-nemotron-3-ultra-550b-a55b-bf16", "name": "Nvidia Nemotron 3 Ultra 550b A55b Bf16"}, "url": "/models/nvidia/nvidia-nemotron-3-ultra-550b-a55b-bf16"}, "performance_score": 14.7479, "efficiency_score": 19.3199, "efficiency_performance_score": 81.1133, "average_output_tokens": 22179.5, "benchmark_count": 2, "performance_scope": "livebench+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.1818, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "nemotron-3-ultra-550b-a55b", "score": 73.491995, "normalized_score": 73.491995, "output_tokens_per_case": 41654.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Nemotron 3 Ultra 550B (high)", "score": 66.66, "normalized_score": 66.66, "output_tokens_per_case": 2705.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 43, "efficiency_rank": 11}, {"model": {"canonical_id": "google-deepmind/gemini-2.5-flash-lite", "name": "Gemini 2.5 Flash-Lite", "organization": {"slug": "google-deepmind", "name": "Google DeepMind", "logo_url": "https://storage.googleapis.com/gdm-deepmind-com-prod-public/icons/google_deepmind_48dp.svg"}, "family": {"slug": "gemini-2-5", "name": "Gemini 2 5"}, "url": "/models/google-deepmind/gemini-2-5-flash-lite"}, "performance_score": 10.7352, "efficiency_score": 19.2011, "efficiency_performance_score": 70.6273, "average_output_tokens": 2374.0, "benchmark_count": 2, "performance_scope": "bfcl+tonebench", "efficiency_scope": "tonebench", "efficiency_benchmark_count": 1, "coverage": 0.1818, "efficiency_coverage": 0.3333, "selected_runs": [{"benchmark": "bfcl", "version": "v4-ede5081a24bc", "configuration": "Gemini-2.5-Flash-Lite (Prompt)", "score": 28.03, "normalized_score": 28.03, "output_tokens_per_case": null, "source_url": "https://gorilla.cs.berkeley.edu/data_overall.csv", "token_source_url": null, "verification_status": "verified_recomputed"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Gemini 2.5 Flash-Lite (no thinking)", "score": 60.69, "normalized_score": 60.69, "output_tokens_per_case": 2374.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 46, "efficiency_rank": 12}, {"model": {"canonical_id": "openai/gpt-oss-120b", "name": "gpt-oss-120b", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-oss-120b", "name": "Gpt Oss 120b"}, "url": "/models/openai/gpt-oss-120b"}, "performance_score": 21.2807, "efficiency_score": 15.2102, "efficiency_performance_score": 71.0011, "average_output_tokens": 6327.82, "benchmark_count": 3, "performance_scope": "aider-polyglot+lmarena-text+tonebench", "efficiency_scope": "aider-polyglot+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.2727, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "aider-polyglot", "version": "polyglot-225-5dc9490bb35f", "configuration": "diff; aider 0.85.3.dev", "score": 41.777778, "normalized_score": 41.777778, "output_tokens_per_case": 3806.64, "source_url": "https://github.com/Aider-AI/aider/blob/5dc9490bb35f9729ef2c95d00a19ccd30c26339c/aider/website/_data/polyglot_leaderboard.yml", "token_source_url": "https://github.com/Aider-AI/aider/blob/5dc9490bb35f9729ef2c95d00a19ccd30c26339c/aider/website/_data/polyglot_leaderboard.yml", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "gpt-oss-120b; 95% CI [1361.16495776, 1369.85717870]; votes 30206; rank 192", "score": 1365.511068, "normalized_score": 45.517036, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "gpt-oss 120B (high)", "score": 61.29, "normalized_score": 61.29, "output_tokens_per_case": 8849.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 33, "efficiency_rank": 13}, {"model": {"canonical_id": "openai/gpt-6-luna", "name": "GPT-6 Luna", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-6", "name": "Gpt 6"}, "url": "/models/openai/gpt-6-luna"}, "performance_score": 46.7777, "efficiency_score": 9.8763, "efficiency_performance_score": 89.1728, "average_output_tokens": 21232.0, "benchmark_count": 6, "performance_scope": "arc-agi-1+arc-agi-2+livebench+lmarena-search+lmarena-text+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.5455, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "GPT-6 Luna (Max)", "score": 86.666667, "normalized_score": 86.666667, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "GPT-6 Luna (Max)", "score": 59.305556, "normalized_score": 59.305556, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "gpt-6-luna-max", "score": 75.837013, "normalized_score": 75.837013, "output_tokens_per_case": 35869.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-search", "version": "search-2026-10-13-a64ca3b12b6e", "configuration": "gpt-6-luna-max; 95% CI [1152.33057533, 1166.78316335]; votes 10793; rank 32", "score": 1159.556869, "normalized_score": 38.651896, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/search/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "gpt-6-luna-max; 95% CI [1387.01005073, 1396.24774606]; votes 49617; rank 166", "score": 1391.628898, "normalized_score": 46.38763, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "GPT-6 Luna (max)", "score": 78.19, "normalized_score": 78.19, "output_tokens_per_case": 6595.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 8, "efficiency_rank": 14}, {"model": {"canonical_id": "thinkingmachines/Inkling", "name": "Inkling", "organization": {"slug": "thinkingmachines", "name": "Thinking Machines Lab", "logo_url": "https://thinkingmachines.ai/images/apple-touch-icon.png"}, "family": {"slug": "inkling", "name": "Inkling"}, "url": "/models/thinkingmachines/inkling"}, "performance_score": 41.7806, "efficiency_score": 8.9628, "efficiency_performance_score": 84.0566, "average_output_tokens": 14605.5, "benchmark_count": 6, "performance_scope": "arc-agi-1+arc-agi-2+livebench+lmarena-agent+lmarena-text+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.5455, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "Inkling", "score": 79.5, "normalized_score": 79.5, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "Inkling", "score": 36.527778, "normalized_score": 36.527778, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "inkling-xhigh", "score": 76.470779, "normalized_score": 76.470779, "output_tokens_per_case": 22213.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-agent", "version": "agent-2026-10-16-a64ca3b12b6e", "configuration": "Inkling; 95% CI [-15.81859883, -12.88168979]; sessions 43507; observations 1662352; rank 50", "score": -14.350144, "normalized_score": 42.824928, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/agent/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "inkling; 95% CI [1437.08506747, 1445.68368363]; votes 40648; rank 74", "score": 1441.384376, "normalized_score": 48.046146, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Inkling (high)", "score": 68.77, "normalized_score": 68.77, "output_tokens_per_case": 6998.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 11, "efficiency_rank": 15}, {"model": {"canonical_id": "google-deepmind/gemini-3.1-pro-preview", "name": "Gemini 3.1 Pro", "organization": {"slug": "google-deepmind", "name": "Google DeepMind", "logo_url": "https://storage.googleapis.com/gdm-deepmind-com-prod-public/icons/google_deepmind_48dp.svg"}, "family": {"slug": "gemini-3", "name": "Gemini 3"}, "url": "/models/google-deepmind/gemini-3-1-pro-preview"}, "performance_score": 66.4669, "efficiency_score": 8.1208, "efficiency_performance_score": 88.3373, "average_output_tokens": 11704.5, "benchmark_count": 8, "performance_scope": "arc-agi-1+arc-agi-2+livebench+lmarena-agent+lmarena-document+lmarena-search+lmarena-vision+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.7273, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "Gemini 3.1 Pro (Preview)", "score": 98.0, "normalized_score": 98.0, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "Gemini 3.1 Pro (Preview)", "score": 77.08, "normalized_score": 77.08, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "gemini-3.1-pro-preview-high", "score": 81.660565, "normalized_score": 81.660565, "output_tokens_per_case": 13380.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-agent", "version": "agent-2026-10-16-a64ca3b12b6e", "configuration": "Gemini 3.1 Pro Preview; 95% CI [-5.35690873, -2.63856355]; sessions 87236; observations 2815597; rank 39", "score": -3.997736, "normalized_score": 48.001132, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/agent/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-document", "version": "document-2026-09-13-a64ca3b12b6e", "configuration": "gemini-3.1-pro-preview; 95% CI [1438.69417039, 1449.14324048]; votes 49457; rank 31", "score": 1443.918705, "normalized_score": 48.130624, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/document/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-search", "version": "search-2026-10-13-a64ca3b12b6e", "configuration": "gemini-3.1-pro-grounding; 95% CI [1204.12797055, 1213.48336905]; votes 151436; rank 15", "score": 1208.80567, "normalized_score": 40.293522, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/search/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "gemini-3.1-pro-preview; 95% CI [1291.04958388, 1301.35691905]; votes 46320; rank 22", "score": 1296.203251, "normalized_score": 43.206775, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Gemini 3.1 Pro (high thinking)", "score": 70.99, "normalized_score": 70.99, "output_tokens_per_case": 10029.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 3, "efficiency_rank": 16}, {"model": {"canonical_id": "openai/gpt-6-astra", "name": "GPT-6 Astra", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-6", "name": "Gpt 6"}, "url": "/models/openai/gpt-6-astra"}, "performance_score": 71.3396, "efficiency_score": 6.8414, "efficiency_performance_score": 97.7003, "average_output_tokens": 15428.0, "benchmark_count": 8, "performance_scope": "arc-agi-1+arc-agi-2+livebench+lmarena-document+lmarena-search+lmarena-text+lmarena-vision+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.7273, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "GPT-6 Astra (XHigh)", "score": 98.5, "normalized_score": 98.5, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "GPT-6 Astra (Max)", "score": 95.0, "normalized_score": 95.0, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "gpt-6-astra-max", "score": 86.47107, "normalized_score": 86.47107, "output_tokens_per_case": 10407.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-document", "version": "document-2026-09-13-a64ca3b12b6e", "configuration": "gpt-6-astra-max; 95% CI [1453.25995337, 1481.78626802]; votes 1621; rank 16", "score": 1467.523111, "normalized_score": 48.917437, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/document/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-search", "version": "search-2026-10-13-a64ca3b12b6e", "configuration": "gpt-6-astra-max; 95% CI [1225.77363708, 1241.45798456]; votes 18483; rank 7", "score": 1233.615811, "normalized_score": 41.120527, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/search/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "gpt-6-astra-max; 95% CI [1436.40189535, 1448.98654490]; votes 12163; rank 69", "score": 1442.69422, "normalized_score": 48.089807, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "gpt-6-astra-max; 95% CI [1270.63592513, 1292.07239183]; votes 3590; rank 36", "score": 1281.354158, "normalized_score": 42.711805, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "GPT-6 Astra (max)", "score": 82.32, "normalized_score": 82.32, "output_tokens_per_case": 20449.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 2, "efficiency_rank": 17}, {"model": {"canonical_id": "openai/gpt-6.1-sol", "name": "GPT-6.1 Sol", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-6", "name": "Gpt 6"}, "url": "/models/openai/gpt-6.1-sol"}, "performance_score": 62.4917, "efficiency_score": 6.7327, "efficiency_performance_score": 97.5789, "average_output_tokens": 15798.0, "benchmark_count": 7, "performance_scope": "arc-agi-1+arc-agi-2+livebench+lmarena-search+lmarena-text+lmarena-vision+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.6364, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "GPT-6.1 Sol (XHigh)", "score": 98.5, "normalized_score": 98.5, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "GPT-6.1 Sol (Max)", "score": 94.166667, "normalized_score": 94.166667, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "gpt-6.1-sol-max", "score": 86.138965, "normalized_score": 86.138965, "output_tokens_per_case": 10375.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-search", "version": "search-2026-10-13-a64ca3b12b6e", "configuration": "gpt-6.1-sol-max; 95% CI [1224.24145466, 1241.96324521]; votes 5555; rank 8", "score": 1233.10235, "normalized_score": 41.103412, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/search/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "gpt-6.1-sol-max; 95% CI [1439.59979847, 1455.74908604]; votes 6320; rank 57", "score": 1447.674442, "normalized_score": 48.255815, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "gpt-6.1-sol-max; 95% CI [1273.83724449, 1302.54208160]; votes 1813; rank 30", "score": 1288.189663, "normalized_score": 42.939655, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "GPT-6.1 Sol (max)", "score": 82.44, "normalized_score": 82.44, "output_tokens_per_case": 21221.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 4, "efficiency_rank": 18}, {"model": {"canonical_id": "moonshotai/Kimi-K3", "name": "Kimi-K3", "organization": {"slug": "moonshotai", "name": "Moonshot AI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/641c1e77c3983aa9490f8121/X1yT2rsaIbR9cdYGEVu0X.jpeg"}, "family": {"slug": "kimi-k3", "name": "Kimi K3"}, "url": "/models/moonshotai/kimi-k3"}, "performance_score": 39.813, "efficiency_score": 5.6088, "efficiency_performance_score": 94.5081, "average_output_tokens": 17542.5, "benchmark_count": 5, "performance_scope": "arc-agi-1+arc-agi-2+livebench+lmarena-agent+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.4545, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "Kimi K3 (Max)", "score": 94.5, "normalized_score": 94.5, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "Kimi K3 (Max)", "score": 60.416667, "normalized_score": 60.416667, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "kimi-k3", "score": 81.019178, "normalized_score": 81.019178, "output_tokens_per_case": 13647.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-agent", "version": "agent-2026-10-16-a64ca3b12b6e", "configuration": "Kimi K3 (Max); 95% CI [1.20183745, 2.66737332]; sessions 135415; observations 12343129; rank 23", "score": 1.934605, "normalized_score": 50.967303, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/agent/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Kimi K3 (max)", "score": 82.23, "normalized_score": 82.23, "output_tokens_per_case": 21438.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 14, "efficiency_rank": 19}, {"model": {"canonical_id": "openai/gpt-5.6-terra", "name": "GPT-5.6 Terra", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-5-6", "name": "Gpt 5 6"}, "url": "/models/openai/gpt-5-6-terra"}, "performance_score": 60.6496, "efficiency_score": 4.6589, "efficiency_performance_score": 94.7709, "average_output_tokens": 21431.5, "benchmark_count": 7, "performance_scope": "arc-agi-1+arc-agi-2+livebench+lmarena-document+lmarena-text+lmarena-vision+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.6364, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "GPT-5.6 Terra (Max)", "score": 96.5, "normalized_score": 96.5, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "GPT-5.6 Terra (Max)", "score": 83.9, "normalized_score": 83.9, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "gpt-5.6-terra-max", "score": 82.314061, "normalized_score": 82.314061, "output_tokens_per_case": 22145.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-document", "version": "document-2026-09-13-a64ca3b12b6e", "configuration": "gpt-5.6-terra-xhigh; 95% CI [1463.31179298, 1479.85049651]; votes 5787; rank 13", "score": 1471.581145, "normalized_score": 49.052705, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/document/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "gpt-5.6-terra-xhigh; 95% CI [1443.15823569, 1451.62460535]; votes 43271; rank 58", "score": 1447.391421, "normalized_score": 48.246381, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "gpt-5.6-terra-xhigh; 95% CI [1263.65540928, 1278.48964371]; votes 11020; rank 43", "score": 1271.072527, "normalized_score": 42.369084, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "GPT-5.6 Terra (ultra)", "score": 81.4, "normalized_score": 81.4, "output_tokens_per_case": 20718.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 5, "efficiency_rank": 20}, {"model": {"canonical_id": "deepseek-ai/DeepSeek-V4-Pro", "name": "DeepSeek-V4-Pro", "organization": {"slug": "deepseek-ai", "name": "DeepSeek", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6538815d1bdb3c40db94fbfa/xMBly9PUMphrFVMxLX4kq.png"}, "family": {"slug": "deepseek-v4-pro", "name": "Deepseek V4 Pro"}, "url": "/models/deepseek-ai/deepseek-v4-pro"}, "performance_score": 24.6674, "efficiency_score": 4.0696, "efficiency_performance_score": 86.7402, "average_output_tokens": 26469.0, "benchmark_count": 3, "performance_scope": "livebench+lmarena-text+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.2727, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "deepseek-v4-pro", "score": 76.786076, "normalized_score": 76.786076, "output_tokens_per_case": 35014.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "deepseek-v4-pro; 95% CI [1447.27741116, 1455.03943137]; votes 57594; rank 49", "score": 1451.158421, "normalized_score": 48.371947, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "DeepSeek V4 Pro (xhigh)", "score": 73.07, "normalized_score": 73.07, "output_tokens_per_case": 17924.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 27, "efficiency_rank": 21}, {"model": {"canonical_id": "MiniMaxAI/MiniMax-M3", "name": "MiniMax-M3", "organization": {"slug": "minimaxai", "name": "MiniMax", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/676e38ad04af5bec20bc9faf/dUd-LsZEX0H_d4qefO_g6.jpeg"}, "family": {"slug": "minimax-m3", "name": "Minimax M3"}, "url": "/models/minimaxai/minimax-m3"}, "performance_score": 41.3218, "efficiency_score": 3.8465, "efficiency_performance_score": 83.9824, "average_output_tokens": 23653.5, "benchmark_count": 5, "performance_scope": "livebench+lmarena-document+lmarena-text+lmarena-vision+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.4545, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "minimax-m3", "score": 70.259864, "normalized_score": 70.259864, "output_tokens_per_case": 15530.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-document", "version": "document-2026-09-13-a64ca3b12b6e", "configuration": "minimax-m3; 95% CI [1426.53255805, 1443.05504941]; votes 6314; rank 32", "score": 1434.793804, "normalized_score": 47.82646, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/document/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "minimax-m3; 95% CI [1429.51159020, 1437.14164071]; votes 63973; rank 91", "score": 1433.326615, "normalized_score": 47.777554, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "minimax-m3; 95% CI [1246.68252453, 1259.53765792]; votes 19026; rank 60", "score": 1253.110091, "normalized_score": 41.770336, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "MiniMax M3 (thinking on)", "score": 74.79, "normalized_score": 74.79, "output_tokens_per_case": 31777.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 12, "efficiency_rank": 22}, {"model": {"canonical_id": "qwen/qwen3.8-max", "name": "Qwen3.8-Max", "organization": {"slug": "qwen", "name": "Qwen", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6215ca5692c0ecfba9186921/hrRM50-6XcdWgg2AKpENG.jpeg"}, "family": {"slug": "qwen3-8-max", "name": "Qwen3 8 Max"}, "url": "/models/qwen/qwen3-8-max"}, "performance_score": 43.9428, "efficiency_score": 3.6727, "efficiency_performance_score": 91.8615, "average_output_tokens": 25738.0, "benchmark_count": 5, "performance_scope": "livebench+lmarena-search+lmarena-text+lmarena-vision+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.4545, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "qwen3.8-max", "score": 81.879613, "normalized_score": 81.879613, "output_tokens_per_case": 21637.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-search", "version": "search-2026-10-13-a64ca3b12b6e", "configuration": "qwen3.8-max; 95% CI [1247.89214823, 1274.26022415]; votes 1870; rank 2", "score": 1261.076186, "normalized_score": 42.035873, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/search/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "qwen3.8-max; 95% CI [1477.92809424, 1487.82635626]; votes 27766; rank 17", "score": 1482.877225, "normalized_score": 49.429241, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "qwen3.8-max; 95% CI [1306.14335895, 1321.05468944]; votes 10017; rank 9", "score": 1313.599024, "normalized_score": 43.786634, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Qwen3.8 Max (thinking on)", "score": 76.83, "normalized_score": 76.83, "output_tokens_per_case": 29839.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 10, "efficiency_rank": 23}, {"model": {"canonical_id": "deepseek-ai/DeepSeek-V4.1-Flash", "name": "DeepSeek-V4.1-Flash", "organization": {"slug": "deepseek-ai", "name": "DeepSeek", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6538815d1bdb3c40db94fbfa/xMBly9PUMphrFVMxLX4kq.png"}, "family": {"slug": "deepseek-v4-1", "name": "Deepseek V4 1"}, "url": "/models/deepseek-ai/deepseek-v4-1-flash"}, "performance_score": 32.9841, "efficiency_score": 3.4848, "efficiency_performance_score": 95.0659, "average_output_tokens": 30683.5, "benchmark_count": 4, "performance_scope": "arc-agi-1+arc-agi-2+livebench+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.3636, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "DeepSeek V4.1 Flash (Max)", "score": 94.5, "normalized_score": 94.5, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "DeepSeek V4.1 Flash (Max)", "score": 72.916667, "normalized_score": 72.916667, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "deepseek-v4.1-flash-max", "score": 83.20017, "normalized_score": 83.20017, "output_tokens_per_case": 36355.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "DeepSeek V4.1 Flash (max)", "score": 81.03, "normalized_score": 81.03, "output_tokens_per_case": 25012.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 19, "efficiency_rank": 24}, {"model": {"canonical_id": "google-deepmind/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "organization": {"slug": "google-deepmind", "name": "Google DeepMind", "logo_url": "https://storage.googleapis.com/gdm-deepmind-com-prod-public/icons/google_deepmind_48dp.svg"}, "family": {"slug": "gemini-3", "name": "Gemini 3"}, "url": "/models/google-deepmind/gemini-3-8-flash"}, "performance_score": 50.8525, "efficiency_score": 3.4576, "efficiency_performance_score": 87.4253, "average_output_tokens": 31577.5, "benchmark_count": 6, "performance_scope": "arc-agi-1+arc-agi-2+livebench+lmarena-agent+lmarena-vision+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.5455, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "Gemini 3.8 Flash (High)", "score": 98.5, "normalized_score": 98.5, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "Gemini 3.8 Flash (High)", "score": 89.166667, "normalized_score": 89.166667, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "gemini-3.8-flash-high", "score": 80.854991, "normalized_score": 80.854991, "output_tokens_per_case": 42786.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-agent", "version": "agent-2026-10-16-a64ca3b12b6e", "configuration": "Gemini 3.8 Flash (High); 95% CI [2.64957678, 4.84993702]; sessions 37692; observations 5316787; rank 15", "score": 3.749757, "normalized_score": 51.874878, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/agent/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "gemini-3.8-flash-high; 95% CI [1303.54395703, 1324.61562115]; votes 3792; rank 8", "score": 1314.079789, "normalized_score": 43.80266, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Gemini 3.8 Flash (high thinking)", "score": 70.22, "normalized_score": 70.22, "output_tokens_per_case": 20369.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 7, "efficiency_rank": 25}, {"model": {"canonical_id": "anthropic/claude-fable-5-1", "name": "Claude Fable 5.1", "organization": {"slug": "anthropic", "name": "Anthropic", "logo_url": "https://platform.claude.com/favicon.ico"}, "family": {"slug": "claude-5-1", "name": "Claude 5 1"}, "url": "/models/anthropic/claude-fable-5-1"}, "performance_score": 71.8986, "efficiency_score": 3.3468, "efficiency_performance_score": 99.1854, "average_output_tokens": 42561.5, "benchmark_count": 8, "performance_scope": "arc-agi-1+arc-agi-2+livebench+lmarena-agent+lmarena-document+lmarena-search+lmarena-vision+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.7273, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "Claude Fable 5.1 (Max)", "score": 97.5, "normalized_score": 97.5, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "Claude Fable 5.1 (XHigh)", "score": 90.0, "normalized_score": 90.0, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "claude-fable-5-1-max-effort", "score": 86.816836, "normalized_score": 86.816836, "output_tokens_per_case": 16470.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-agent", "version": "agent-2026-10-16-a64ca3b12b6e", "configuration": "Claude Fable 5.1 (Max); 95% CI [12.03932907, 16.02502568]; sessions 16374; observations 1913479; rank 3", "score": 14.032177, "normalized_score": 57.016089, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/agent/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-document", "version": "document-2026-09-13-a64ca3b12b6e", "configuration": "claude-fable-5.1-max; 95% CI [1497.40364732, 1527.76498981]; votes 1403; rank 2", "score": 1512.584319, "normalized_score": 50.419477, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/document/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-search", "version": "search-2026-10-13-a64ca3b12b6e", "configuration": "claude-fable-5.1-high; 95% CI [1238.79268797, 1252.89817971]; votes 12782; rank 5", "score": 1245.845434, "normalized_score": 41.528181, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/search/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "claude-fable-5.1-max; 95% CI [1308.61778049, 1327.86146111]; votes 4648; rank 4", "score": 1318.239621, "normalized_score": 43.941321, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Claude Fable 5.1 (max effort)", "score": 84.53, "normalized_score": 84.53, "output_tokens_per_case": 68653.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 1, "efficiency_rank": 26}, {"model": {"canonical_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "organization": {"slug": "anthropic", "name": "Anthropic", "logo_url": "https://platform.claude.com/favicon.ico"}, "family": {"slug": "claude-5", "name": "Claude 5"}, "url": "/models/anthropic/claude-sonnet-5"}, "performance_score": 51.5341, "efficiency_score": 2.781, "efficiency_performance_score": 92.1724, "average_output_tokens": 43190.5, "benchmark_count": 6, "performance_scope": "livebench+lmarena-agent+lmarena-document+lmarena-text+lmarena-vision+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.5455, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "claude-sonnet-5-xhigh-effort", "score": 80.014756, "normalized_score": 80.014756, "output_tokens_per_case": 19428.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-agent", "version": "agent-2026-10-16-a64ca3b12b6e", "configuration": "Claude Sonnet 5 (High); 95% CI [2.88280252, 6.28024714]; sessions 33276; observations 3570560; rank 12", "score": 4.581525, "normalized_score": 52.290762, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/agent/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-document", "version": "document-2026-09-13-a64ca3b12b6e", "configuration": "claude-sonnet-5-high; 95% CI [1458.49407458, 1473.77896309]; votes 7411; rank 17", "score": 1466.136519, "normalized_score": 48.871217, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/document/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "claude-sonnet-5-high; 95% CI [1438.01344792, 1446.22951308]; votes 49595; rank 72", "score": 1442.12148, "normalized_score": 48.070716, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "claude-sonnet-5-high; 95% CI [1267.02186706, 1280.81063637]; votes 13503; rank 41", "score": 1273.916252, "normalized_score": 42.463875, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Claude Sonnet 5 (max effort)", "score": 79.21, "normalized_score": 79.21, "output_tokens_per_case": 66953.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 6, "efficiency_rank": 27}, {"model": {"canonical_id": "moonshotai/Kimi-K2.7-Code", "name": "Kimi K2.7 Code", "organization": {"slug": "moonshotai", "name": "Moonshot AI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/641c1e77c3983aa9490f8121/X1yT2rsaIbR9cdYGEVu0X.jpeg"}, "family": {"slug": "kimi-k2-7", "name": "Kimi K2 7"}, "url": "/models/moonshotai/kimi-k2-7-code"}, "performance_score": 7.4815, "efficiency_score": 2.5239, "efficiency_performance_score": 82.2968, "average_output_tokens": 13007.0, "benchmark_count": 1, "performance_scope": "livebench", "efficiency_scope": "livebench", "efficiency_benchmark_count": 1, "coverage": 0.0909, "efficiency_coverage": 0.3333, "selected_runs": [{"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "kimi-k2.7-code", "score": 71.447447, "normalized_score": 71.447447, "output_tokens_per_case": 13007.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}], "performance_rank": 61, "efficiency_rank": 28}, {"model": {"canonical_id": "zai-org/glm-5.3-flash", "name": "GLM-5.3-Flash", "organization": {"slug": "zai-org", "name": "Z.ai", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/62dc173789b4cf157d36ebee/i_pxzM2ZDo3Ub-BEgIkE9.png"}, "family": {"slug": "glm-5-3-flash", "name": "Glm 5 3 Flash"}, "url": "/models/zai-org/glm-5-3-flash"}, "performance_score": 34.2815, "efficiency_score": 2.4949, "efficiency_performance_score": 89.8071, "average_output_tokens": 37504.0, "benchmark_count": 4, "performance_scope": "livebench+lmarena-text+lmarena-vision+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.3636, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "glm-5.3-flash", "score": 73.270866, "normalized_score": 73.270866, "output_tokens_per_case": 34707.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "glm-5.3-flash; 95% CI [1465.67476412, 1475.38456118]; votes 32925; rank 29", "score": 1470.529663, "normalized_score": 49.017655, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "glm-5.3-flash; 95% CI [1288.97978191, 1303.07121064]; votes 11157; rank 23", "score": 1296.025496, "normalized_score": 43.20085, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "GLM-5.3 Flash (max)", "score": 81.82, "normalized_score": 81.82, "output_tokens_per_case": 40301.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 18, "efficiency_rank": 29}, {"model": {"canonical_id": "qwen/qwen3.8-flash", "name": "Qwen3.8-Flash", "organization": {"slug": "qwen", "name": "Qwen", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6215ca5692c0ecfba9186921/hrRM50-6XcdWgg2AKpENG.jpeg"}, "family": {"slug": "qwen3-8-flash", "name": "Qwen3 8 Flash"}, "url": "/models/qwen/qwen3-8-flash"}, "performance_score": 16.2513, "efficiency_score": 2.4581, "efficiency_performance_score": 89.3821, "average_output_tokens": 43014.0, "benchmark_count": 2, "performance_scope": "livebench+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.1818, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "qwen3.8-flash-next", "score": 79.120246, "normalized_score": 79.120246, "output_tokens_per_case": 54438.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Qwen3.8 Flash (thinking on)", "score": 75.3, "normalized_score": 75.3, "output_tokens_per_case": 31590.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 41, "efficiency_rank": 30}, {"model": {"canonical_id": "anthropic/claude-opus-5-5", "name": "Claude Opus 5.5", "organization": {"slug": "anthropic", "name": "Anthropic", "logo_url": "https://platform.claude.com/favicon.ico"}, "family": {"slug": "claude-5-5", "name": "Claude 5 5"}, "url": "/models/anthropic/claude-opus-5-5"}, "performance_score": 44.855, "efficiency_score": 2.0522, "efficiency_performance_score": 99.4958, "average_output_tokens": 76047.5, "benchmark_count": 5, "performance_scope": "arc-agi-1+arc-agi-2+livebench+lmarena-search+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.4545, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "Claude Opus 5.5 (High)", "score": 98.5, "normalized_score": 98.5, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "Claude Opus 5.5 (High)", "score": 93.333333, "normalized_score": 93.333333, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "claude-opus-5-5-max-effort", "score": 85.941291, "normalized_score": 85.941291, "output_tokens_per_case": 25610.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-search", "version": "search-2026-10-13-a64ca3b12b6e", "configuration": "claude-opus-5.5-medium; 95% CI [1205.66309681, 1219.84195206]; votes 10842; rank 14", "score": 1212.752524, "normalized_score": 40.425084, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/search/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Claude Opus 5.5 (max effort)", "score": 85.93, "normalized_score": 85.93, "output_tokens_per_case": 126485.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 9, "efficiency_rank": 31}, {"model": {"canonical_id": "xai/grok-4.7", "name": "Grok 4.7", "organization": {"slug": "xai", "name": "xAI", "logo_url": "https://x.ai/favicon.ico"}, "family": {"slug": "grok-4", "name": "Grok 4"}, "url": "/models/xai/grok-4-7"}, "performance_score": 39.4513, "efficiency_score": 1.9657, "efficiency_performance_score": 93.6481, "average_output_tokens": 51370.0, "benchmark_count": 5, "performance_scope": "arc-agi-1+arc-agi-2+livebench+lmarena-agent+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.4545, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "Grok 4.7 (High)", "score": 90.166667, "normalized_score": 90.166667, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "Grok 4.7 (XHigh)", "score": 61.388889, "normalized_score": 61.388889, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "grok-4.7-xhigh", "score": 82.203353, "normalized_score": 82.203353, "output_tokens_per_case": 56776.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-agent", "version": "agent-2026-10-16-a64ca3b12b6e", "configuration": "Grok 4.7 (xHigh); 95% CI [1.57579589, 4.84117305]; sessions 15127; observations 2475030; rank 16", "score": 3.208484, "normalized_score": 51.604242, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/agent/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "Grok 4.7 (high)", "score": 79.58, "normalized_score": 79.58, "output_tokens_per_case": 45964.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 15, "efficiency_rank": 32}, {"model": {"canonical_id": "zai-org/glm-5.3", "name": "GLM-5.3", "organization": {"slug": "zai-org", "name": "Z.ai", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/62dc173789b4cf157d36ebee/i_pxzM2ZDo3Ub-BEgIkE9.png"}, "family": {"slug": "glm-5-3", "name": "Glm 5 3"}, "url": "/models/zai-org/glm-5-3"}, "performance_score": 26.025, "efficiency_score": 1.8182, "efficiency_performance_score": 93.5225, "average_output_tokens": 56149.0, "benchmark_count": 3, "performance_scope": "livebench+lmarena-text+tonebench", "efficiency_scope": "livebench+tonebench", "efficiency_benchmark_count": 2, "coverage": 0.2727, "efficiency_coverage": 0.6667, "selected_runs": [{"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "glm-5.3", "score": 79.146315, "normalized_score": 79.146315, "output_tokens_per_case": 62090.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "glm-5.3-max; 95% CI [1466.26042381, 1476.65163576]; votes 22543; rank 27", "score": 1471.45603, "normalized_score": 49.048534, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "tonebench", "version": "2026-10-17-10-task-e9c76358afb2", "configuration": "GLM-5.3 (max)", "score": 82.39, "normalized_score": 82.39, "output_tokens_per_case": 50208.0, "source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "token_source_url": "https://benchmark.towardsai.com/data/leaderboard.json", "verification_status": "verified_publisher"}], "performance_rank": 25, "efficiency_rank": 33}, {"model": {"canonical_id": "mistralai/mistral-large-4", "name": "Mistral Large 4", "organization": {"slug": "mistralai", "name": "Mistral AI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/634c17653d11eaedd88b314d/9OgyfKstSZtbmsmuG8MbU.png"}, "family": {"slug": "mistral-large-4", "name": "Mistral Large 4"}, "url": "/models/mistralai/mistral-large-4"}, "performance_score": 8.0286, "efficiency_score": 1.3708, "efficiency_performance_score": 88.3142, "average_output_tokens": 25699.0, "benchmark_count": 1, "performance_scope": "livebench", "efficiency_scope": "livebench", "efficiency_benchmark_count": 1, "coverage": 0.0909, "efficiency_coverage": 0.3333, "selected_runs": [{"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "mistral-large-4-high", "score": 76.671572, "normalized_score": 76.671572, "output_tokens_per_case": 25699.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}], "performance_rank": 57, "efficiency_rank": 34}, {"model": {"canonical_id": "Qwen/Qwen3.8-27B", "name": "Qwen3.8-27B", "organization": {"slug": "qwen", "name": "Qwen", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6215ca5692c0ecfba9186921/hrRM50-6XcdWgg2AKpENG.jpeg"}, "family": {"slug": "qwen3-8-27b", "name": "Qwen3 8 27b"}, "url": "/models/qwen/qwen3-8-27b"}, "performance_score": 37.8988, "efficiency_score": 1.2474, "efficiency_performance_score": 89.8721, "average_output_tokens": 28740.0, "benchmark_count": 5, "performance_scope": "arc-agi-1+arc-agi-2+livebench+lmarena-text+lmarena-vision", "efficiency_scope": "livebench", "efficiency_benchmark_count": 1, "coverage": 0.4545, "efficiency_coverage": 0.3333, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "Qwen3.8-27B (XHigh)", "score": 87.5, "normalized_score": 87.5, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "Qwen3.8-27B (XHigh)", "score": 42.361111, "normalized_score": 42.361111, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "qwen3.8-27b", "score": 78.024105, "normalized_score": 78.024105, "output_tokens_per_case": 28740.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "qwen3.8-27b; 95% CI [1435.47949951, 1445.61514077]; votes 23294; rank 75", "score": 1440.54732, "normalized_score": 48.018244, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "qwen3.8-27b; 95% CI [1262.99100972, 1279.79432635]; votes 7013; rank 42", "score": 1271.392668, "normalized_score": 42.379756, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}], "performance_rank": 16, "efficiency_rank": 35}, {"model": {"canonical_id": "openai/gpt-5.4-nano", "name": "GPT-5.4 Nano", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-5-4", "name": "Gpt 5 4"}, "url": "/models/openai/gpt-5-4-nano"}, "performance_score": 29.8379, "efficiency_score": 0.7489, "efficiency_performance_score": 86.6955, "average_output_tokens": 46179.0, "benchmark_count": 5, "performance_scope": "arc-agi-1+arc-agi-2+livebench+lmarena-text+lmarena-vision", "efficiency_scope": "livebench", "efficiency_benchmark_count": 1, "coverage": 0.4545, "efficiency_coverage": 0.3333, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "GPT-5.4 Nano (XHigh)", "score": 51.5, "normalized_score": 51.5, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "GPT-5.4 Nano (XHigh)", "score": 5.69, "normalized_score": 5.69, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "gpt-5.4-nano-xhigh", "score": 75.266301, "normalized_score": 75.266301, "output_tokens_per_case": 46179.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "gpt-5.4-nano-high; 95% CI [1368.25704083, 1375.76986498]; votes 62396; rank 182", "score": 1372.013453, "normalized_score": 45.733782, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "gpt-5.4-nano-high; 95% CI [1189.64874058, 1202.27965668]; votes 25650; rank 94", "score": 1195.964199, "normalized_score": 39.865473, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}], "performance_rank": 21, "efficiency_rank": 36}, {"model": {"canonical_id": "openai/gpt-5.4-mini", "name": "GPT-5.4 Mini", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-5-4", "name": "Gpt 5 4"}, "url": "/models/openai/gpt-5-4-mini"}, "performance_score": 32.2047, "efficiency_score": 0.6733, "efficiency_performance_score": 80.0885, "average_output_tokens": 47448.0, "benchmark_count": 5, "performance_scope": "arc-agi-1+arc-agi-2+livebench+lmarena-text+lmarena-vision", "efficiency_scope": "livebench", "efficiency_benchmark_count": 1, "coverage": 0.4545, "efficiency_coverage": 0.3333, "selected_runs": [{"benchmark": "arc-agi-1", "version": "verified-v1-613c385b0c93", "configuration": "GPT-5.4 Mini (XHigh)", "score": 63.67, "normalized_score": 63.67, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v1.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "arc-agi-2", "version": "verified-v2-be40992860f9", "configuration": "GPT-5.4 Mini (XHigh)", "score": 18.9, "normalized_score": 18.9, "output_tokens_per_case": null, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "livebench", "version": "2026-06-25-90f8d44da965", "configuration": "gpt-5.4-mini-xhigh", "score": 69.530263, "normalized_score": 69.530263, "output_tokens_per_case": 47448.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "token_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/cost_2026_06_25.csv", "verification_status": "verified_recomputed"}, {"benchmark": "lmarena-text", "version": "text-2026-10-15-a64ca3b12b6e", "configuration": "gpt-5.4-mini-high; 95% CI [1407.73358875, 1415.16901218]; votes 63449; rank 137", "score": 1411.4513, "normalized_score": 47.048377, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/text/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}, {"benchmark": "lmarena-vision", "version": "vision-2026-10-09-a64ca3b12b6e", "configuration": "gpt-5.4-mini-high; 95% CI [1238.81649273, 1251.21275945]; votes 25733; rank 68", "score": 1245.014626, "normalized_score": 41.500488, "output_tokens_per_case": null, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/a64ca3b12b6e6fcb9e7747cd56131d8a8047d822/vision/latest-00000-of-00001.parquet", "token_source_url": null, "verification_status": "verified_publisher"}], "performance_rank": 20, "efficiency_rank": 37}], "frontier": [{"model": {"canonical_id": "anthropic/claude-opus-5-5", "name": "Claude Opus 5.5", "organization": {"slug": "anthropic", "name": "Anthropic", "logo_url": "https://platform.claude.com/favicon.ico"}, "family": {"slug": "claude-5-5", "name": "Claude 5 5"}, "url": "/models/anthropic/claude-opus-5-5"}, "configuration": "Claude Opus 5.5 (max effort)", "performance_score": 85.93, "efficiency_score": 1.5308, "average_output_tokens": 126485.0, "is_frontier": true}, {"model": {"canonical_id": "anthropic/claude-opus-5-5", "name": "Claude Opus 5.5", "organization": {"slug": "anthropic", "name": "Anthropic", "logo_url": "https://platform.claude.com/favicon.ico"}, "family": {"slug": "claude-5-5", "name": "Claude 5 5"}, "url": "/models/anthropic/claude-opus-5-5"}, "configuration": "Claude Opus 5.5 (xhigh)", "performance_score": 85.83, "efficiency_score": 4.0695, "average_output_tokens": 47524.0, "is_frontier": true}, {"model": {"canonical_id": "anthropic/claude-opus-5-5", "name": "Claude Opus 5.5", "organization": {"slug": "anthropic", "name": "Anthropic", "logo_url": "https://platform.claude.com/favicon.ico"}, "family": {"slug": "claude-5-5", "name": "Claude 5 5"}, "url": "/models/anthropic/claude-opus-5-5"}, "configuration": "Claude Opus 5.5 (high)", "performance_score": 84.61, "efficiency_score": 13.8371, "average_output_tokens": 13778.0, "is_frontier": true}, {"model": {"canonical_id": "anthropic/claude-fable-5-1", "name": "Claude Fable 5.1", "organization": {"slug": "anthropic", "name": "Anthropic", "logo_url": "https://platform.claude.com/favicon.ico"}, "family": {"slug": "claude-5-1", "name": "Claude 5 1"}, "url": "/models/anthropic/claude-fable-5-1"}, "configuration": "Claude Fable 5.1 (max effort)", "performance_score": 84.53, "efficiency_score": 2.7744, "average_output_tokens": 68653.0, "is_frontier": false}, {"model": {"canonical_id": "anthropic/claude-opus-5-5", "name": "Claude Opus 5.5", "organization": {"slug": "anthropic", "name": "Anthropic", "logo_url": "https://platform.claude.com/favicon.ico"}, "family": {"slug": "claude-5-5", "name": "Claude 5 5"}, "url": "/models/anthropic/claude-opus-5-5"}, "configuration": "Claude Opus 5.5 (medium)", "performance_score": 84.49, "efficiency_score": 14.8039, "average_output_tokens": 12860.0, "is_frontier": true}, {"model": {"canonical_id": "anthropic/claude-opus-5-5", "name": "Claude Opus 5.5", "organization": {"slug": "anthropic", "name": "Anthropic", "logo_url": "https://platform.claude.com/favicon.ico"}, "family": {"slug": "claude-5-5", "name": "Claude 5 5"}, "url": "/models/anthropic/claude-opus-5-5"}, "configuration": "Claude Opus 5.5 (low)", "performance_score": 84.28, "efficiency_score": 19.9752, "average_output_tokens": 9507.0, "is_frontier": true}, {"model": {"canonical_id": "anthropic/claude-fable-5-1", "name": "Claude Fable 5.1", "organization": {"slug": "anthropic", "name": "Anthropic", "logo_url": "https://platform.claude.com/favicon.ico"}, "family": {"slug": "claude-5-1", "name": "Claude 5 1"}, "url": "/models/anthropic/claude-fable-5-1"}, "configuration": "Claude Fable 5.1 (high)", "performance_score": 83.41, "efficiency_score": 5.482, "average_output_tokens": 34284.0, "is_frontier": false}, {"model": {"canonical_id": "openai/gpt-6.1-sol", "name": "GPT-6.1 Sol", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-6", "name": "Gpt 6"}, "url": "/models/openai/gpt-6.1-sol"}, "configuration": "GPT-6.1 Sol (max)", "performance_score": 82.44, "efficiency_score": 8.7535, "average_output_tokens": 21221.0, "is_frontier": false}, {"model": {"canonical_id": "zai-org/glm-5.3", "name": "GLM-5.3", "organization": {"slug": "zai-org", "name": "Z.ai", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/62dc173789b4cf157d36ebee/i_pxzM2ZDo3Ub-BEgIkE9.png"}, "family": {"slug": "glm-5-3", "name": "Glm 5 3"}, "url": "/models/zai-org/glm-5-3"}, "configuration": "GLM-5.3 (max)", "performance_score": 82.39, "efficiency_score": 3.6975, "average_output_tokens": 50208.0, "is_frontier": false}, {"model": {"canonical_id": "openai/gpt-6.1-sol", "name": "GPT-6.1 Sol", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-6", "name": "Gpt 6"}, "url": "/models/openai/gpt-6.1-sol"}, "configuration": "GPT-6.1 Sol (xhigh)", "performance_score": 82.39, "efficiency_score": 10.7565, "average_output_tokens": 17259.0, "is_frontier": false}, {"model": {"canonical_id": "openai/gpt-6-astra", "name": "GPT-6 Astra", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-6", "name": "Gpt 6"}, "url": "/models/openai/gpt-6-astra"}, "configuration": "GPT-6 Astra (max)", "performance_score": 82.32, "efficiency_score": 9.0708, "average_output_tokens": 20449.0, "is_frontier": false}, {"model": {"canonical_id": "moonshotai/Kimi-K3", "name": "Kimi-K3", "organization": {"slug": "moonshotai", "name": "Moonshot AI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/641c1e77c3983aa9490f8121/X1yT2rsaIbR9cdYGEVu0X.jpeg"}, "family": {"slug": "kimi-k3", "name": "Kimi K3"}, "url": "/models/moonshotai/kimi-k3"}, "configuration": "Kimi K3 (max)", "performance_score": 82.23, "efficiency_score": 8.6429, "average_output_tokens": 21438.0, "is_frontier": false}, {"model": {"canonical_id": "zai-org/glm-5.3-flash", "name": "GLM-5.3-Flash", "organization": {"slug": "zai-org", "name": "Z.ai", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/62dc173789b4cf157d36ebee/i_pxzM2ZDo3Ub-BEgIkE9.png"}, "family": {"slug": "glm-5-3-flash", "name": "Glm 5 3 Flash"}, "url": "/models/zai-org/glm-5-3-flash"}, "configuration": "GLM-5.3 Flash (max)", "performance_score": 81.82, "efficiency_score": 4.5746, "average_output_tokens": 40301.0, "is_frontier": false}, {"model": {"canonical_id": "openai/gpt-6.1-sol", "name": "GPT-6.1 Sol", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-6", "name": "Gpt 6"}, "url": "/models/openai/gpt-6.1-sol"}, "configuration": "GPT-6.1 Sol (low)", "performance_score": 81.41, "efficiency_score": 71.7114, "average_output_tokens": 2558.0, "is_frontier": true}, {"model": {"canonical_id": "openai/gpt-5.6-terra", "name": "GPT-5.6 Terra", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-5-6", "name": "Gpt 5 6"}, "url": "/models/openai/gpt-5-6-terra"}, "configuration": "GPT-5.6 Terra (ultra)", "performance_score": 81.4, "efficiency_score": 8.8529, "average_output_tokens": 20718.0, "is_frontier": false}, {"model": {"canonical_id": "openai/gpt-6.1-sol", "name": "GPT-6.1 Sol", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-6", "name": "Gpt 6"}, "url": "/models/openai/gpt-6.1-sol"}, "configuration": "GPT-6.1 Sol (high)", "performance_score": 81.12, "efficiency_score": 26.8682, "average_output_tokens": 6803.0, "is_frontier": false}, {"model": {"canonical_id": "deepseek-ai/DeepSeek-V4.1-Flash", "name": "DeepSeek-V4.1-Flash", "organization": {"slug": "deepseek-ai", "name": "DeepSeek", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6538815d1bdb3c40db94fbfa/xMBly9PUMphrFVMxLX4kq.png"}, "family": {"slug": "deepseek-v4-1", "name": "Deepseek V4 1"}, "url": "/models/deepseek-ai/deepseek-v4-1-flash"}, "configuration": "DeepSeek V4.1 Flash (max)", "performance_score": 81.03, "efficiency_score": 7.2998, "average_output_tokens": 25012.0, "is_frontier": false}, {"model": {"canonical_id": "openai/gpt-6.1-sol", "name": "GPT-6.1 Sol", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-6", "name": "Gpt 6"}, "url": "/models/openai/gpt-6.1-sol"}, "configuration": "GPT-6.1 Sol (medium)", "performance_score": 81.0, "efficiency_score": 67.0514, "average_output_tokens": 2722.0, "is_frontier": false}, {"model": {"canonical_id": "openai/gpt-6-astra", "name": "GPT-6 Astra", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-6", "name": "Gpt 6"}, "url": "/models/openai/gpt-6-astra"}, "configuration": "GPT-6 Astra (medium)", "performance_score": 80.67, "efficiency_score": 69.6438, "average_output_tokens": 2610.0, "is_frontier": false}, {"model": {"canonical_id": "openai/gpt-5.6-terra", "name": "GPT-5.6 Terra", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-5-6", "name": "Gpt 5 6"}, "url": "/models/openai/gpt-5-6-terra"}, "configuration": "GPT-5.6 Terra (medium)", "performance_score": 80.66, "efficiency_score": 61.4428, "average_output_tokens": 2958.0, "is_frontier": false}, {"model": {"canonical_id": "deepseek-ai/DeepSeek-V4.1-Flash", "name": "DeepSeek-V4.1-Flash", "organization": {"slug": "deepseek-ai", "name": "DeepSeek", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6538815d1bdb3c40db94fbfa/xMBly9PUMphrFVMxLX4kq.png"}, "family": {"slug": "deepseek-v4-1", "name": "Deepseek V4 1"}, "url": "/models/deepseek-ai/deepseek-v4-1-flash"}, "configuration": "DeepSeek V4.1 Flash (high)", "performance_score": 80.35, "efficiency_score": 10.8621, "average_output_tokens": 16668.0, "is_frontier": false}, {"model": {"canonical_id": "moonshotai/Kimi-K3", "name": "Kimi-K3", "organization": {"slug": "moonshotai", "name": "Moonshot AI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/641c1e77c3983aa9490f8121/X1yT2rsaIbR9cdYGEVu0X.jpeg"}, "family": {"slug": "kimi-k3", "name": "Kimi K3"}, "url": "/models/moonshotai/kimi-k3"}, "configuration": "Kimi K3 (high)", "performance_score": 80.35, "efficiency_score": 30.9433, "average_output_tokens": 5851.0, "is_frontier": false}, {"model": {"canonical_id": "xai/grok-4.7", "name": "Grok 4.7", "organization": {"slug": "xai", "name": "xAI", "logo_url": "https://x.ai/favicon.ico"}, "family": {"slug": "grok-4", "name": "Grok 4"}, "url": "/models/xai/grok-4-7"}, "configuration": "Grok 4.7 (medium)", "performance_score": 79.6, "efficiency_score": 5.7794, "average_output_tokens": 31034.0, "is_frontier": false}, {"model": {"canonical_id": "xai/grok-4.7", "name": "Grok 4.7", "organization": {"slug": "xai", "name": "xAI", "logo_url": "https://x.ai/favicon.ico"}, "family": {"slug": "grok-4", "name": "Grok 4"}, "url": "/models/xai/grok-4-7"}, "configuration": "Grok 4.7 (high)", "performance_score": 79.58, "efficiency_score": 3.9012, "average_output_tokens": 45964.0, "is_frontier": false}, {"model": {"canonical_id": "deepseek-ai/DeepSeek-V4.1-Flash", "name": "DeepSeek-V4.1-Flash", "organization": {"slug": "deepseek-ai", "name": "DeepSeek", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6538815d1bdb3c40db94fbfa/xMBly9PUMphrFVMxLX4kq.png"}, "family": {"slug": "deepseek-v4-1", "name": "Deepseek V4 1"}, "url": "/models/deepseek-ai/deepseek-v4-1-flash"}, "configuration": "DeepSeek V4.1 Flash (low)", "performance_score": 79.3, "efficiency_score": 19.021, "average_output_tokens": 9394.0, "is_frontier": false}, {"model": {"canonical_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "organization": {"slug": "anthropic", "name": "Anthropic", "logo_url": "https://platform.claude.com/favicon.ico"}, "family": {"slug": "claude-5", "name": "Claude 5"}, "url": "/models/anthropic/claude-sonnet-5"}, "configuration": "Claude Sonnet 5 (max effort)", "performance_score": 79.21, "efficiency_score": 2.6658, "average_output_tokens": 66953.0, "is_frontier": false}, {"model": {"canonical_id": "xai/grok-4.7", "name": "Grok 4.7", "organization": {"slug": "xai", "name": "xAI", "logo_url": "https://x.ai/favicon.ico"}, "family": {"slug": "grok-4", "name": "Grok 4"}, "url": "/models/xai/grok-4-7"}, "configuration": "Grok 4.7 (low)", "performance_score": 78.95, "efficiency_score": 30.1977, "average_output_tokens": 5891.0, "is_frontier": false}, {"model": {"canonical_id": "openai/gpt-6-luna", "name": "GPT-6 Luna", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-6", "name": "Gpt 6"}, "url": "/models/openai/gpt-6-luna"}, "configuration": "GPT-6 Luna (max)", "performance_score": 78.19, "efficiency_score": 26.7145, "average_output_tokens": 6595.0, "is_frontier": false}, {"model": {"canonical_id": "openai/gpt-6-luna", "name": "GPT-6 Luna", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-6", "name": "Gpt 6"}, "url": "/models/openai/gpt-6-luna"}, "configuration": "GPT-6 Luna (high)", "performance_score": 77.39, "efficiency_score": 57.1737, "average_output_tokens": 3050.0, "is_frontier": false}, {"model": {"canonical_id": "openai/gpt-6-luna", "name": "GPT-6 Luna", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-6", "name": "Gpt 6"}, "url": "/models/openai/gpt-6-luna"}, "configuration": "GPT-6 Luna (medium)", "performance_score": 76.96, "efficiency_score": 66.1873, "average_output_tokens": 2620.0, "is_frontier": false}, {"model": {"canonical_id": "qwen/qwen3.8-max", "name": "Qwen3.8-Max", "organization": {"slug": "qwen", "name": "Qwen", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6215ca5692c0ecfba9186921/hrRM50-6XcdWgg2AKpENG.jpeg"}, "family": {"slug": "qwen3-8-max", "name": "Qwen3 8 Max"}, "url": "/models/qwen/qwen3-8-max"}, "configuration": "Qwen3.8 Max (thinking on)", "performance_score": 76.83, "efficiency_score": 5.8017, "average_output_tokens": 29839.0, "is_frontier": false}, {"model": {"canonical_id": "deepseek-ai/DeepSeek-V4.1-Flash", "name": "DeepSeek-V4.1-Flash", "organization": {"slug": "deepseek-ai", "name": "DeepSeek", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6538815d1bdb3c40db94fbfa/xMBly9PUMphrFVMxLX4kq.png"}, "family": {"slug": "deepseek-v4-1", "name": "Deepseek V4 1"}, "url": "/models/deepseek-ai/deepseek-v4-1-flash"}, "configuration": "DeepSeek V4.1 Flash (no thinking)", "performance_score": 76.81, "efficiency_score": 60.8768, "average_output_tokens": 2843.0, "is_frontier": false}, {"model": {"canonical_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "organization": {"slug": "anthropic", "name": "Anthropic", "logo_url": "https://platform.claude.com/favicon.ico"}, "family": {"slug": "claude-5", "name": "Claude 5"}, "url": "/models/anthropic/claude-sonnet-5"}, "configuration": "Claude Sonnet 5 (high)", "performance_score": 76.62, "efficiency_score": 18.2635, "average_output_tokens": 9453.0, "is_frontier": false}, {"model": {"canonical_id": "qwen/qwen3.8-flash", "name": "Qwen3.8-Flash", "organization": {"slug": "qwen", "name": "Qwen", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6215ca5692c0ecfba9186921/hrRM50-6XcdWgg2AKpENG.jpeg"}, "family": {"slug": "qwen3-8-flash", "name": "Qwen3 8 Flash"}, "url": "/models/qwen/qwen3-8-flash"}, "configuration": "Qwen3.8 Flash (thinking on)", "performance_score": 75.3, "efficiency_score": 5.371, "average_output_tokens": 31590.0, "is_frontier": false}, {"model": {"canonical_id": "MiniMaxAI/MiniMax-M3", "name": "MiniMax-M3", "organization": {"slug": "minimaxai", "name": "MiniMax", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/676e38ad04af5bec20bc9faf/dUd-LsZEX0H_d4qefO_g6.jpeg"}, "family": {"slug": "minimax-m3", "name": "Minimax M3"}, "url": "/models/minimaxai/minimax-m3"}, "configuration": "MiniMax M3 (thinking on)", "performance_score": 74.79, "efficiency_score": 5.3032, "average_output_tokens": 31777.0, "is_frontier": false}, {"model": {"canonical_id": "deepseek-ai/DeepSeek-V4-Pro", "name": "DeepSeek-V4-Pro", "organization": {"slug": "deepseek-ai", "name": "DeepSeek", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6538815d1bdb3c40db94fbfa/xMBly9PUMphrFVMxLX4kq.png"}, "family": {"slug": "deepseek-v4-pro", "name": "Deepseek V4 Pro"}, "url": "/models/deepseek-ai/deepseek-v4-pro"}, "configuration": "DeepSeek V4 Pro (high)", "performance_score": 73.62, "efficiency_score": 26.1113, "average_output_tokens": 6353.0, "is_frontier": false}, {"model": {"canonical_id": "deepseek-ai/DeepSeek-V4-Pro", "name": "DeepSeek-V4-Pro", "organization": {"slug": "deepseek-ai", "name": "DeepSeek", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6538815d1bdb3c40db94fbfa/xMBly9PUMphrFVMxLX4kq.png"}, "family": {"slug": "deepseek-v4-pro", "name": "Deepseek V4 Pro"}, "url": "/models/deepseek-ai/deepseek-v4-pro"}, "configuration": "DeepSeek V4 Pro (xhigh)", "performance_score": 73.07, "efficiency_score": 9.1858, "average_output_tokens": 17924.0, "is_frontier": false}, {"model": {"canonical_id": "google-deepmind/gemini-3.1-pro-preview", "name": "Gemini 3.1 Pro", "organization": {"slug": "google-deepmind", "name": "Google DeepMind", "logo_url": "https://storage.googleapis.com/gdm-deepmind-com-prod-public/icons/google_deepmind_48dp.svg"}, "family": {"slug": "gemini-3", "name": "Gemini 3"}, "url": "/models/google-deepmind/gemini-3-1-pro-preview"}, "configuration": "Gemini 3.1 Pro (high thinking)", "performance_score": 70.99, "efficiency_score": 15.9496, "average_output_tokens": 10029.0, "is_frontier": false}, {"model": {"canonical_id": "google-deepmind/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "organization": {"slug": "google-deepmind", "name": "Google DeepMind", "logo_url": "https://storage.googleapis.com/gdm-deepmind-com-prod-public/icons/google_deepmind_48dp.svg"}, "family": {"slug": "gemini-3", "name": "Gemini 3"}, "url": "/models/google-deepmind/gemini-3-8-flash"}, "configuration": "Gemini 3.8 Flash (high thinking)", "performance_score": 70.22, "efficiency_score": 7.7679, "average_output_tokens": 20369.0, "is_frontier": false}, {"model": {"canonical_id": "google-deepmind/gemini-3.1-pro-preview", "name": "Gemini 3.1 Pro", "organization": {"slug": "google-deepmind", "name": "Google DeepMind", "logo_url": "https://storage.googleapis.com/gdm-deepmind-com-prod-public/icons/google_deepmind_48dp.svg"}, "family": {"slug": "gemini-3", "name": "Gemini 3"}, "url": "/models/google-deepmind/gemini-3-1-pro-preview"}, "configuration": "Gemini 3.1 Pro (low thinking)", "performance_score": 70.14, "efficiency_score": 24.4915, "average_output_tokens": 6453.0, "is_frontier": false}, {"model": {"canonical_id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct", "name": "Llama-4-Maverick-17B-128E-Instruct", "organization": {"slug": "meta-llama", "name": "Meta", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/646cf8084eefb026fb8fd8bc/oCTqufkdTkjyGodsx1vo1.png"}, "family": {"slug": "llama-4-maverick-17b-128e-instruct", "name": "Llama 4 Maverick 17b 128e Instruct"}, "url": "/models/meta-llama/llama-4-maverick-17b-128e-instruct"}, "configuration": "Llama 4 Maverick (no thinking)", "performance_score": 69.93, "efficiency_score": 70.5961, "average_output_tokens": 2232.0, "is_frontier": true}, {"model": {"canonical_id": "google-deepmind/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "organization": {"slug": "google-deepmind", "name": "Google DeepMind", "logo_url": "https://storage.googleapis.com/gdm-deepmind-com-prod-public/icons/google_deepmind_48dp.svg"}, "family": {"slug": "gemini-3", "name": "Gemini 3"}, "url": "/models/google-deepmind/gemini-3-8-flash"}, "configuration": "Gemini 3.8 Flash (medium thinking)", "performance_score": 69.13, "efficiency_score": 22.9239, "average_output_tokens": 6795.0, "is_frontier": false}, {"model": {"canonical_id": "thinkingmachines/Inkling", "name": "Inkling", "organization": {"slug": "thinkingmachines", "name": "Thinking Machines Lab", "logo_url": "https://thinkingmachines.ai/images/apple-touch-icon.png"}, "family": {"slug": "inkling", "name": "Inkling"}, "url": "/models/thinkingmachines/inkling"}, "configuration": "Inkling (high)", "performance_score": 68.77, "efficiency_score": 22.143, "average_output_tokens": 6998.0, "is_frontier": false}, {"model": {"canonical_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", "name": "NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", "organization": {"slug": "nvidia", "name": "NVIDIA", "logo_url": "https://www.nvidia.com/etc/designs/nvidiaGDC/clientlibs_base/images/NVIDIA-Logo.svg"}, "family": {"slug": "nvidia-nemotron-3-ultra-550b-a55b-bf16", "name": "Nvidia Nemotron 3 Ultra 550b A55b Bf16"}, "url": "/models/nvidia/nvidia-nemotron-3-ultra-550b-a55b-bf16"}, "configuration": "Nemotron 3 Ultra 550B (high)", "performance_score": 66.66, "efficiency_score": 55.5276, "average_output_tokens": 2705.0, "is_frontier": false}, {"model": {"canonical_id": "google-deepmind/gemini-3.5-flash-lite", "name": "Gemini 3.5 Flash-Lite", "organization": {"slug": "google-deepmind", "name": "Google DeepMind", "logo_url": "https://storage.googleapis.com/gdm-deepmind-com-prod-public/icons/google_deepmind_48dp.svg"}, "family": {"slug": "gemini-3", "name": "Gemini 3"}, "url": "/models/google-deepmind/gemini-3-5-flash-lite"}, "configuration": "Gemini 3.5 Flash-Lite (minimal thinking)", "performance_score": 65.0, "efficiency_score": 72.1487, "average_output_tokens": 2030.0, "is_frontier": true}, {"model": {"canonical_id": "mistralai/mistral-large-2512", "name": "Mistral Large 3", "organization": {"slug": "mistralai", "name": "Mistral AI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/634c17653d11eaedd88b314d/9OgyfKstSZtbmsmuG8MbU.png"}, "family": {"slug": "mistral-large-3", "name": "Mistral Large 3"}, "url": "/models/mistralai/mistral-large-2512"}, "configuration": "Mistral Large 3 (no thinking)", "performance_score": 61.78, "efficiency_score": 68.5408, "average_output_tokens": 2031.0, "is_frontier": false}, {"model": {"canonical_id": "openai/gpt-oss-120b", "name": "gpt-oss-120b", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-oss-120b", "name": "Gpt Oss 120b"}, "url": "/models/openai/gpt-oss-120b"}, "configuration": "gpt-oss 120B (high)", "performance_score": 61.29, "efficiency_score": 15.6065, "average_output_tokens": 8849.0, "is_frontier": false}, {"model": {"canonical_id": "google-deepmind/gemini-2.5-flash-lite", "name": "Gemini 2.5 Flash-Lite", "organization": {"slug": "google-deepmind", "name": "Google DeepMind", "logo_url": "https://storage.googleapis.com/gdm-deepmind-com-prod-public/icons/google_deepmind_48dp.svg"}, "family": {"slug": "gemini-2-5", "name": "Gemini 2 5"}, "url": "/models/google-deepmind/gemini-2-5-flash-lite"}, "configuration": "Gemini 2.5 Flash-Lite (no thinking)", "performance_score": 60.69, "efficiency_score": 57.6033, "average_output_tokens": 2374.0, "is_frontier": false}, {"model": {"canonical_id": "openai/gpt-oss-120b", "name": "gpt-oss-120b", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-oss-120b", "name": "Gpt Oss 120b"}, "url": "/models/openai/gpt-oss-120b"}, "configuration": "gpt-oss 120B (medium)", "performance_score": 60.13, "efficiency_score": 49.7205, "average_output_tokens": 2725.0, "is_frontier": false}, {"model": {"canonical_id": "coherelabs/command-a-reasoning-08-2025", "name": "Command A Reasoning", "organization": {"slug": "coherelabs", "name": "Cohere", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678549441248-5e70f6048ce3c604d78fe133.png"}, "family": {"slug": "command-a", "name": "Command A"}, "url": "/models/coherelabs/command-a-reasoning-08-2025"}, "configuration": "Cohere Command A Reasoning (thinking on)", "performance_score": 52.73, "efficiency_score": 62.0117, "average_output_tokens": 1916.0, "is_frontier": true}, {"model": {"canonical_id": "coherelabs/command-a-03-2025", "name": "Command A", "organization": {"slug": "coherelabs", "name": "Cohere", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678549441248-5e70f6048ce3c604d78fe133.png"}, "family": {"slug": "command-a", "name": "Command A"}, "url": "/models/coherelabs/command-a-03-2025"}, "configuration": "Cohere Command A (03-2025) (no thinking)", "performance_score": 49.68, "efficiency_score": 95.2697, "average_output_tokens": 1175.0, "is_frontier": true}, {"model": {"canonical_id": "openai/gpt-4o", "name": "GPT-4o", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-4o", "name": "Gpt 4o"}, "url": "/models/openai/gpt-4o"}, "configuration": "GPT-4o (no thinking)", "performance_score": 47.32, "efficiency_score": 95.6271, "average_output_tokens": 1115.0, "is_frontier": true}, {"model": {"canonical_id": "openai/gpt-4o-mini", "name": "GPT-4o Mini", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-4o", "name": "Gpt 4o"}, "url": "/models/openai/gpt-4o-mini"}, "configuration": "GPT-4o mini (no thinking)", "performance_score": 46.95, "efficiency_score": 79.0071, "average_output_tokens": 1339.0, "is_frontier": false}, {"model": {"canonical_id": "meta-llama/Llama-4-Scout-17B-16E-Instruct", "name": "Llama-4-Scout-17B-16E-Instruct", "organization": {"slug": "meta-llama", "name": "Meta", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/646cf8084eefb026fb8fd8bc/oCTqufkdTkjyGodsx1vo1.png"}, "family": {"slug": "llama-4-scout-17b-16e-instruct", "name": "Llama 4 Scout 17b 16e Instruct"}, "url": "/models/meta-llama/llama-4-scout-17b-16e-instruct"}, "configuration": "Llama 4 Scout (no thinking)", "performance_score": 37.59, "efficiency_score": 100.0, "average_output_tokens": 847.0, "is_frontier": true}], "quality_cost": [{"model": {"canonical_id": "xai/grok-build-0.1", "name": "Grok Build 0.1", "organization": {"slug": "xai", "name": "xAI", "logo_url": "https://x.ai/favicon.ico"}, "family": {"slug": "grok-build", "name": "Grok Build"}, "url": "/models/xai/grok-build-0-1"}, "configuration": "grok-build-0.1", "performance_score": 71.0948, "average_output_tokens": 980.0, "output_price_per_million": 2.0, "estimated_output_cost_per_case": 0.00196, "score_adjusted_output_cost": 0.002757, "price_provider": {"slug": "xai", "name": "Xai", "logo_url": "https://x.ai/favicon.ico"}, "price_source_url": "https://docs.x.ai/developers/pricing", "price_observed_at": "2026-09-03T04:30:00+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "is_frontier": true}, {"model": {"canonical_id": "zai-org/glm-5.3-flash", "name": "GLM-5.3-Flash", "organization": {"slug": "zai-org", "name": "Z.ai", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/62dc173789b4cf157d36ebee/i_pxzM2ZDo3Ub-BEgIkE9.png"}, "family": {"slug": "glm-5-3-flash", "name": "Glm 5 3 Flash"}, "url": "/models/zai-org/glm-5-3-flash"}, "configuration": "glm-5.3-flash", "performance_score": 73.2709, "average_output_tokens": 34707.0, "output_price_per_million": 0.25, "estimated_output_cost_per_case": 0.008677, "score_adjusted_output_cost": 0.011842, "price_provider": {"slug": "zai", "name": "Z.ai", "logo_url": "https://modelmarkets.ai/organization-logos/zai.svg"}, "price_source_url": "https://docs.z.ai/guides/overview/pricing#glm-5-3-flash", "price_observed_at": "2026-08-29T23:45:00+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "is_frontier": true}, {"model": {"canonical_id": "openai/gpt-6-luna", "name": "GPT-6 Luna", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-6", "name": "Gpt 6"}, "url": "/models/openai/gpt-6-luna"}, "configuration": "gpt-6-luna-max", "performance_score": 75.837, "average_output_tokens": 35869.0, "output_price_per_million": 0.5, "estimated_output_cost_per_case": 0.017934, "score_adjusted_output_cost": 0.023649, "price_provider": {"slug": "openai", "name": "Openai", "logo_url": "https://developers.openai.com/favicon.svg"}, "price_source_url": "https://developers.openai.com/api/docs/models/gpt-6-luna#pricing", "price_observed_at": "2026-09-22T18:43:47+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "is_frontier": true}, {"model": {"canonical_id": "MiniMaxAI/MiniMax-M3", "name": "MiniMax-M3", "organization": {"slug": "minimaxai", "name": "MiniMax", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/676e38ad04af5bec20bc9faf/dUd-LsZEX0H_d4qefO_g6.jpeg"}, "family": {"slug": "minimax-m3", "name": "Minimax M3"}, "url": "/models/minimaxai/minimax-m3"}, "configuration": "minimax-m3", "performance_score": 70.2599, "average_output_tokens": 15530.0, "output_price_per_million": 1.1, "estimated_output_cost_per_case": 0.017083, "score_adjusted_output_cost": 0.024314, "price_provider": {"slug": "deepinfra", "name": "Deepinfra", "logo_url": "https://deepinfra.com/fav-192.png"}, "price_source_url": "https://api.deepinfra.com/v1/openai/models", "price_observed_at": "2026-10-19T12:23:41.821613+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "is_frontier": false}, {"model": {"canonical_id": "deepseek-ai/DeepSeek-V4.1-Flash", "name": "DeepSeek-V4.1-Flash", "organization": {"slug": "deepseek-ai", "name": "DeepSeek", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6538815d1bdb3c40db94fbfa/xMBly9PUMphrFVMxLX4kq.png"}, "family": {"slug": "deepseek-v4-1", "name": "Deepseek V4 1"}, "url": "/models/deepseek-ai/deepseek-v4-1-flash"}, "configuration": "deepseek-v4.1-flash-max", "performance_score": 83.2002, "average_output_tokens": 36355.0, "output_price_per_million": 0.6, "estimated_output_cost_per_case": 0.021813, "score_adjusted_output_cost": 0.026217, "price_provider": {"slug": "deepseek", "name": "DeepSeek", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6538815d1bdb3c40db94fbfa/xMBly9PUMphrFVMxLX4kq.png"}, "price_source_url": "https://api-docs.deepseek.com/quick_start/pricing/", "price_observed_at": "2026-09-10T14:35:33+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "is_frontier": true}, {"model": {"canonical_id": "qwen/qwen3.8-flash", "name": "Qwen3.8-Flash", "organization": {"slug": "qwen", "name": "Qwen", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6215ca5692c0ecfba9186921/hrRM50-6XcdWgg2AKpENG.jpeg"}, "family": {"slug": "qwen3-8-flash", "name": "Qwen3 8 Flash"}, "url": "/models/qwen/qwen3-8-flash"}, "configuration": "qwen3.8-flash-next", "performance_score": 79.1202, "average_output_tokens": 54438.0, "output_price_per_million": 0.382, "estimated_output_cost_per_case": 0.020795, "score_adjusted_output_cost": 0.026283, "price_provider": {"slug": "deepinfra", "name": "Deepinfra", "logo_url": "https://deepinfra.com/fav-192.png"}, "price_source_url": "https://api.deepinfra.com/v1/openai/models", "price_observed_at": "2026-10-19T12:23:41.821613+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "is_frontier": false}, {"model": {"canonical_id": "google-deepmind/gemini-3.5-flash-lite", "name": "Gemini 3.5 Flash-Lite", "organization": {"slug": "google-deepmind", "name": "Google DeepMind", "logo_url": "https://storage.googleapis.com/gdm-deepmind-com-prod-public/icons/google_deepmind_48dp.svg"}, "family": {"slug": "gemini-3", "name": "Gemini 3"}, "url": "/models/google-deepmind/gemini-3-5-flash-lite"}, "configuration": "gemini-3.5-flash-lite-high", "performance_score": 66.3466, "average_output_tokens": 11526.0, "output_price_per_million": 2.5, "estimated_output_cost_per_case": 0.028815, "score_adjusted_output_cost": 0.043431, "price_provider": {"slug": "google-ai", "name": "Google AI", "logo_url": "https://deepmind.google/favicon.ico"}, "price_source_url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash-lite", "price_observed_at": "2026-08-29T19:00:00+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "is_frontier": false}, {"model": {"canonical_id": "moonshotai/Kimi-K2.7-Code", "name": "Kimi K2.7 Code", "organization": {"slug": "moonshotai", "name": "Moonshot AI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/641c1e77c3983aa9490f8121/X1yT2rsaIbR9cdYGEVu0X.jpeg"}, "family": {"slug": "kimi-k2-7", "name": "Kimi K2 7"}, "url": "/models/moonshotai/kimi-k2-7-code"}, "configuration": "kimi-k2.7-code", "performance_score": 71.4474, "average_output_tokens": 13007.0, "output_price_per_million": 3.35, "estimated_output_cost_per_case": 0.043573, "score_adjusted_output_cost": 0.060987, "price_provider": {"slug": "openrouter", "name": "Openrouter", "logo_url": "https://openrouter.ai/favicon/glyph.png"}, "price_source_url": "https://openrouter.ai/api/v1/models", "price_observed_at": "2026-10-19T12:39:09.621619+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "is_frontier": false}, {"model": {"canonical_id": "mistralai/mistral-large-4", "name": "Mistral Large 4", "organization": {"slug": "mistralai", "name": "Mistral AI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/634c17653d11eaedd88b314d/9OgyfKstSZtbmsmuG8MbU.png"}, "family": {"slug": "mistral-large-4", "name": "Mistral Large 4"}, "url": "/models/mistralai/mistral-large-4"}, "configuration": "mistral-large-4-high", "performance_score": 76.6716, "average_output_tokens": 25699.0, "output_price_per_million": 2.09, "estimated_output_cost_per_case": 0.053711, "score_adjusted_output_cost": 0.070053, "price_provider": {"slug": "mistral", "name": "Mistral AI", "logo_url": "https://modelmarkets.ai/organization-logos/mistral.svg"}, "price_source_url": "https://docs.mistral.ai/inference/pricing", "price_observed_at": "2026-10-06T14:41:00+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "is_frontier": false}, {"model": {"canonical_id": "deepseek-ai/DeepSeek-V4-Pro", "name": "DeepSeek-V4-Pro", "organization": {"slug": "deepseek-ai", "name": "DeepSeek", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6538815d1bdb3c40db94fbfa/xMBly9PUMphrFVMxLX4kq.png"}, "family": {"slug": "deepseek-v4-pro", "name": "Deepseek V4 Pro"}, "url": "/models/deepseek-ai/deepseek-v4-pro"}, "configuration": "deepseek-v4-pro", "performance_score": 76.7861, "average_output_tokens": 35014.0, "output_price_per_million": 1.544076, "estimated_output_cost_per_case": 0.054064, "score_adjusted_output_cost": 0.070409, "price_provider": {"slug": "openrouter", "name": "Openrouter", "logo_url": "https://openrouter.ai/favicon/glyph.png"}, "price_source_url": "https://openrouter.ai/api/v1/model/deepseek/deepseek-v4-pro", "price_observed_at": "2026-08-28T16:49:00+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "is_frontier": false}, {"model": {"canonical_id": "openai/gpt-5.4-nano", "name": "GPT-5.4 Nano", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-5-4", "name": "Gpt 5 4"}, "url": "/models/openai/gpt-5-4-nano"}, "configuration": "gpt-5.4-nano-xhigh", "performance_score": 75.2663, "average_output_tokens": 46179.0, "output_price_per_million": 1.25, "estimated_output_cost_per_case": 0.057724, "score_adjusted_output_cost": 0.076693, "price_provider": {"slug": "openai", "name": "Openai", "logo_url": "https://developers.openai.com/favicon.svg"}, "price_source_url": "https://developers.openai.com/api/docs/models/gpt-5.4-nano#pricing", "price_observed_at": "2026-09-03T04:30:00+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "is_frontier": false}, {"model": {"canonical_id": "Qwen/Qwen3.8-27B", "name": "Qwen3.8-27B", "organization": {"slug": "qwen", "name": "Qwen", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6215ca5692c0ecfba9186921/hrRM50-6XcdWgg2AKpENG.jpeg"}, "family": {"slug": "qwen3-8-27b", "name": "Qwen3 8 27b"}, "url": "/models/qwen/qwen3-8-27b"}, "configuration": "qwen3.8-27b", "performance_score": 78.0241, "average_output_tokens": 28740.0, "output_price_per_million": 2.2, "estimated_output_cost_per_case": 0.063228, "score_adjusted_output_cost": 0.081036, "price_provider": {"slug": "openrouter", "name": "Openrouter", "logo_url": "https://openrouter.ai/favicon/glyph.png"}, "price_source_url": "https://openrouter.ai/api/v1/models", "price_observed_at": "2026-10-19T12:39:09.621619+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "is_frontier": false}, {"model": {"canonical_id": "thinkingmachines/Inkling", "name": "Inkling", "organization": {"slug": "thinkingmachines", "name": "Thinking Machines Lab", "logo_url": "https://thinkingmachines.ai/images/apple-touch-icon.png"}, "family": {"slug": "inkling", "name": "Inkling"}, "url": "/models/thinkingmachines/inkling"}, "configuration": "inkling-xhigh", "performance_score": 76.4708, "average_output_tokens": 22213.0, "output_price_per_million": 4.05, "estimated_output_cost_per_case": 0.089963, "score_adjusted_output_cost": 0.117643, "price_provider": {"slug": "deepinfra", "name": "Deepinfra", "logo_url": "https://deepinfra.com/fav-192.png"}, "price_source_url": "https://api.deepinfra.com/v1/openai/models", "price_observed_at": "2026-10-15T08:23:35.581686+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "is_frontier": false}, {"model": {"canonical_id": "openai/gpt-6.1-sol", "name": "GPT-6.1 Sol", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-6", "name": "Gpt 6"}, "url": "/models/openai/gpt-6.1-sol"}, "configuration": "gpt-6.1-sol-max", "performance_score": 86.139, "average_output_tokens": 10375.0, "output_price_per_million": 10.0, "estimated_output_cost_per_case": 0.10375, "score_adjusted_output_cost": 0.120445, "price_provider": {"slug": "openai", "name": "Openai", "logo_url": "https://developers.openai.com/favicon.svg"}, "price_source_url": "https://developers.openai.com/api/docs/models/gpt-6.1-sol#pricing", "price_observed_at": "2026-09-29T19:07:07.591789+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "is_frontier": true}, {"model": {"canonical_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", "name": "NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", "organization": {"slug": "nvidia", "name": "NVIDIA", "logo_url": "https://www.nvidia.com/etc/designs/nvidiaGDC/clientlibs_base/images/NVIDIA-Logo.svg"}, "family": {"slug": "nvidia-nemotron-3-ultra-550b-a55b-bf16", "name": "Nvidia Nemotron 3 Ultra 550b A55b Bf16"}, "url": "/models/nvidia/nvidia-nemotron-3-ultra-550b-a55b-bf16"}, "configuration": "nemotron-3-ultra-550b-a55b", "performance_score": 73.492, "average_output_tokens": 41654.0, "output_price_per_million": 2.2, "estimated_output_cost_per_case": 0.091639, "score_adjusted_output_cost": 0.124692, "price_provider": {"slug": "openrouter", "name": "Openrouter", "logo_url": "https://openrouter.ai/favicon/glyph.png"}, "price_source_url": "https://openrouter.ai/api/v1/model/nvidia/nemotron-3-ultra-550b-a55b", "price_observed_at": "2026-08-29T04:33:54+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "is_frontier": false}, {"model": {"canonical_id": "qwen/qwen3.8-max", "name": "Qwen3.8-Max", "organization": {"slug": "qwen", "name": "Qwen", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6215ca5692c0ecfba9186921/hrRM50-6XcdWgg2AKpENG.jpeg"}, "family": {"slug": "qwen3-8-max", "name": "Qwen3 8 Max"}, "url": "/models/qwen/qwen3-8-max"}, "configuration": "qwen3.8-max", "performance_score": 81.8796, "average_output_tokens": 21637.0, "output_price_per_million": 4.951, "estimated_output_cost_per_case": 0.107125, "score_adjusted_output_cost": 0.130832, "price_provider": {"slug": "deepinfra", "name": "Deepinfra", "logo_url": "https://deepinfra.com/fav-192.png"}, "price_source_url": "https://api.deepinfra.com/v1/openai/models", "price_observed_at": "2026-10-19T12:23:41.821613+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "is_frontier": false}, {"model": {"canonical_id": "google-deepmind/gemini-3.1-pro-preview", "name": "Gemini 3.1 Pro", "organization": {"slug": "google-deepmind", "name": "Google DeepMind", "logo_url": "https://storage.googleapis.com/gdm-deepmind-com-prod-public/icons/google_deepmind_48dp.svg"}, "family": {"slug": "gemini-3", "name": "Gemini 3"}, "url": "/models/google-deepmind/gemini-3-1-pro-preview"}, "configuration": "gemini-3.1-pro-preview-high", "performance_score": 81.6606, "average_output_tokens": 13380.0, "output_price_per_million": 12.0, "estimated_output_cost_per_case": 0.16056, "score_adjusted_output_cost": 0.196619, "price_provider": {"slug": "google-ai", "name": "Google AI", "logo_url": "https://deepmind.google/favicon.ico"}, "price_source_url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview", "price_observed_at": "2026-08-29T19:00:00+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "is_frontier": false}, {"model": {"canonical_id": "google-deepmind/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "organization": {"slug": "google-deepmind", "name": "Google DeepMind", "logo_url": "https://storage.googleapis.com/gdm-deepmind-com-prod-public/icons/google_deepmind_48dp.svg"}, "family": {"slug": "gemini-3", "name": "Gemini 3"}, "url": "/models/google-deepmind/gemini-3-8-flash"}, "configuration": "gemini-3.8-flash-high", "performance_score": 80.855, "average_output_tokens": 42786.0, "output_price_per_million": 3.75, "estimated_output_cost_per_case": 0.160447, "score_adjusted_output_cost": 0.198439, "price_provider": {"slug": "google-ai", "name": "Google AI", "logo_url": "https://deepmind.google/favicon.ico"}, "price_source_url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.8-flash", "price_observed_at": "2026-09-02T20:39:50+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "is_frontier": false}, {"model": {"canonical_id": "moonshotai/Kimi-K3", "name": "Kimi-K3", "organization": {"slug": "moonshotai", "name": "Moonshot AI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/641c1e77c3983aa9490f8121/X1yT2rsaIbR9cdYGEVu0X.jpeg"}, "family": {"slug": "kimi-k3", "name": "Kimi K3"}, "url": "/models/moonshotai/kimi-k3"}, "configuration": "kimi-k3", "performance_score": 81.0192, "average_output_tokens": 13647.0, "output_price_per_million": 11.936, "estimated_output_cost_per_case": 0.162891, "score_adjusted_output_cost": 0.201052, "price_provider": {"slug": "openrouter", "name": "Openrouter", "logo_url": "https://openrouter.ai/favicon/glyph.png"}, "price_source_url": "https://openrouter.ai/api/v1/models", "price_observed_at": "2026-10-19T12:39:09.621619+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "is_frontier": false}, {"model": {"canonical_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "organization": {"slug": "anthropic", "name": "Anthropic", "logo_url": "https://platform.claude.com/favicon.ico"}, "family": {"slug": "claude-5", "name": "Claude 5"}, "url": "/models/anthropic/claude-sonnet-5"}, "configuration": "claude-sonnet-5-xhigh-effort", "performance_score": 80.0148, "average_output_tokens": 19428.0, "output_price_per_million": 10.0, "estimated_output_cost_per_case": 0.19428, "score_adjusted_output_cost": 0.242805, "price_provider": {"slug": "anthropic", "name": "Anthropic", "logo_url": "https://platform.claude.com/favicon.ico"}, "price_source_url": "https://platform.claude.com/docs/en/models/overview", "price_observed_at": "2026-09-03T04:30:00+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "is_frontier": false}, {"model": {"canonical_id": "openai/gpt-5.4-mini", "name": "GPT-5.4 Mini", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-5-4", "name": "Gpt 5 4"}, "url": "/models/openai/gpt-5-4-mini"}, "configuration": "gpt-5.4-mini-xhigh", "performance_score": 69.5303, "average_output_tokens": 47448.0, "output_price_per_million": 4.5, "estimated_output_cost_per_case": 0.213516, "score_adjusted_output_cost": 0.307084, "price_provider": {"slug": "openai", "name": "Openai", "logo_url": "https://developers.openai.com/favicon.svg"}, "price_source_url": "https://developers.openai.com/api/docs/models/gpt-5.4-mini#pricing", "price_observed_at": "2026-09-03T04:30:00+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "is_frontier": false}, {"model": {"canonical_id": "zai-org/glm-5.3", "name": "GLM-5.3", "organization": {"slug": "zai-org", "name": "Z.ai", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/62dc173789b4cf157d36ebee/i_pxzM2ZDo3Ub-BEgIkE9.png"}, "family": {"slug": "glm-5-3", "name": "Glm 5 3"}, "url": "/models/zai-org/glm-5-3"}, "configuration": "glm-5.3", "performance_score": 79.1463, "average_output_tokens": 62090.0, "output_price_per_million": 4.0, "estimated_output_cost_per_case": 0.24836, "score_adjusted_output_cost": 0.313799, "price_provider": {"slug": "deepinfra", "name": "Deepinfra", "logo_url": "https://deepinfra.com/fav-192.png"}, "price_source_url": "https://api.deepinfra.com/v1/openai/models", "price_observed_at": "2026-10-19T12:23:41.821613+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "is_frontier": false}, {"model": {"canonical_id": "openai/gpt-5.6-terra", "name": "GPT-5.6 Terra", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-5-6", "name": "Gpt 5 6"}, "url": "/models/openai/gpt-5-6-terra"}, "configuration": "gpt-5.6-terra-max", "performance_score": 82.3141, "average_output_tokens": 22145.0, "output_price_per_million": 12.0, "estimated_output_cost_per_case": 0.26574, "score_adjusted_output_cost": 0.322837, "price_provider": {"slug": "openai", "name": "Openai", "logo_url": "https://developers.openai.com/favicon.svg"}, "price_source_url": "https://developers.openai.com/api/docs/models/gpt-5.6-terra", "price_observed_at": "2026-09-03T04:30:00+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "is_frontier": false}, {"model": {"canonical_id": "xai/grok-4.7", "name": "Grok 4.7", "organization": {"slug": "xai", "name": "xAI", "logo_url": "https://x.ai/favicon.ico"}, "family": {"slug": "grok-4", "name": "Grok 4"}, "url": "/models/xai/grok-4-7"}, "configuration": "grok-4.7-xhigh", "performance_score": 82.2034, "average_output_tokens": 56776.0, "output_price_per_million": 6.0, "estimated_output_cost_per_case": 0.340656, "score_adjusted_output_cost": 0.414406, "price_provider": {"slug": "xai", "name": "Xai", "logo_url": "https://x.ai/favicon.ico"}, "price_source_url": "https://docs.x.ai/developers/models/grok-4.7#pricing", "price_observed_at": "2026-09-22T06:25:00+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "is_frontier": false}, {"model": {"canonical_id": "anthropic/claude-opus-5-5", "name": "Claude Opus 5.5", "organization": {"slug": "anthropic", "name": "Anthropic", "logo_url": "https://platform.claude.com/favicon.ico"}, "family": {"slug": "claude-5-5", "name": "Claude 5 5"}, "url": "/models/anthropic/claude-opus-5-5"}, "configuration": "claude-opus-5-5-max-effort", "performance_score": 85.9413, "average_output_tokens": 25610.0, "output_price_per_million": 20.0, "estimated_output_cost_per_case": 0.5122, "score_adjusted_output_cost": 0.595988, "price_provider": {"slug": "anthropic", "name": "Anthropic", "logo_url": "https://platform.claude.com/favicon.ico"}, "price_source_url": "https://platform.claude.com/docs/en/models/opus-5-5/overview#pricing", "price_observed_at": "2026-09-22T16:54:00+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "is_frontier": false}, {"model": {"canonical_id": "openai/gpt-6-astra", "name": "GPT-6 Astra", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-6", "name": "Gpt 6"}, "url": "/models/openai/gpt-6-astra"}, "configuration": "gpt-6-astra-max", "performance_score": 86.4711, "average_output_tokens": 10407.0, "output_price_per_million": 50.0, "estimated_output_cost_per_case": 0.52035, "score_adjusted_output_cost": 0.601762, "price_provider": {"slug": "openai", "name": "Openai", "logo_url": "https://developers.openai.com/favicon.svg"}, "price_source_url": "https://developers.openai.com/api/docs/models/gpt-6-astra#pricing", "price_observed_at": "2026-09-04T05:43:28+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "is_frontier": true}, {"model": {"canonical_id": "anthropic/claude-fable-5-1", "name": "Claude Fable 5.1", "organization": {"slug": "anthropic", "name": "Anthropic", "logo_url": "https://platform.claude.com/favicon.ico"}, "family": {"slug": "claude-5-1", "name": "Claude 5 1"}, "url": "/models/anthropic/claude-fable-5-1"}, "configuration": "claude-fable-5-1-max-effort", "performance_score": 86.8168, "average_output_tokens": 16470.0, "output_price_per_million": 50.0, "estimated_output_cost_per_case": 0.8235, "score_adjusted_output_cost": 0.948549, "price_provider": {"slug": "anthropic", "name": "Anthropic", "logo_url": "https://platform.claude.com/favicon.ico"}, "price_source_url": "https://platform.claude.com/docs/en/models/fable-5-1/overview#pricing", "price_observed_at": "2026-09-03T04:30:00+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "is_frontier": true}], "value_efficiency": [{"model": {"canonical_id": "deepseek-ai/DeepSeek-V4.1-Flash", "name": "DeepSeek-V4.1-Flash", "organization": {"slug": "deepseek-ai", "name": "DeepSeek", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6538815d1bdb3c40db94fbfa/xMBly9PUMphrFVMxLX4kq.png"}, "family": {"slug": "deepseek-v4-1", "name": "Deepseek V4 1"}, "url": "/models/deepseek-ai/deepseek-v4-1-flash"}, "efficiency_score": 71.6873, "intelligence_score": 83.264, "affordability_score": 60.1107, "estimated_output_cost_per_case": 0.021813, "intelligence_components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "deepseek-v4.1-flash-max", "raw_score": 83.20017, "score_unit": "percent", "relative_score": 89.0869, "weight": 0.5, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "DeepSeek V4.1 Flash (Max)", "raw_score": 72.916667, "score_unit": "percent", "relative_score": 77.4412, "weight": 0.5, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}], "intelligence_component_count": 2, "intelligence_component_coverage": 0.6667, "intelligence_missing_components": ["lmarena-text"], "intelligence_coverage_status": "partial", "score_range": {"lower": 57.81, "upper": 74.4767}, "price_source_url": "https://api-docs.deepseek.com/quick_start/pricing/", "price_observed_at": "2026-09-10T14:35:33+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "index_version": "1.9-bdd35fc15ff7", "efficiency_rank": 1}, {"model": {"canonical_id": "zai-org/glm-5.3-flash", "name": "GLM-5.3-Flash", "organization": {"slug": "zai-org", "name": "Z.ai", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/62dc173789b4cf157d36ebee/i_pxzM2ZDo3Ub-BEgIkE9.png"}, "family": {"slug": "glm-5-3-flash", "name": "Glm 5 3 Flash"}, "url": "/models/zai-org/glm-5-3-flash"}, "efficiency_score": 65.7937, "intelligence_score": 56.2161, "affordability_score": 75.3712, "estimated_output_cost_per_case": 0.008677, "intelligence_components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "glm-5.3-flash", "raw_score": 73.270866, "score_unit": "percent", "relative_score": 36.6011, "weight": 0.5, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "glm-5.3-flash; 95% CI [1466.06395213, 1475.85820899]; votes 31379; rank 29", "raw_score": 1470.961081, "score_unit": "rating", "relative_score": 75.8311, "weight": 0.5, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "intelligence_component_count": 2, "intelligence_component_coverage": 0.6667, "intelligence_missing_components": ["arc-agi-2"], "intelligence_coverage_status": "partial", "score_range": {"lower": 56.4243, "upper": 73.091}, "price_source_url": "https://docs.z.ai/guides/overview/pricing#glm-5-3-flash", "price_observed_at": "2026-08-29T23:45:00+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "index_version": "1.9-bdd35fc15ff7", "efficiency_rank": 2}, {"model": {"canonical_id": "qwen/qwen3.8-flash", "name": "Qwen3.8-Flash", "organization": {"slug": "qwen", "name": "Qwen", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6215ca5692c0ecfba9186921/hrRM50-6XcdWgg2AKpENG.jpeg"}, "family": {"slug": "qwen3-8-flash", "name": "Qwen3 8 Flash"}, "url": "/models/qwen/qwen3-8-flash"}, "efficiency_score": 64.2112, "intelligence_score": 67.5206, "affordability_score": 60.9019, "estimated_output_cost_per_case": 0.020795, "intelligence_components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "qwen3.8-flash-next", "raw_score": 79.120246, "score_unit": "percent", "relative_score": 67.5206, "weight": 1.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}], "intelligence_component_count": 1, "intelligence_component_coverage": 0.3333, "intelligence_missing_components": ["arc-agi-2", "lmarena-text"], "intelligence_coverage_status": "partial", "score_range": {"lower": 41.7044, "upper": 75.0377}, "price_source_url": "https://api.deepinfra.com/v1/openai/models", "price_observed_at": "2026-10-19T12:23:41.821613+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "index_version": "1.9-bdd35fc15ff7", "efficiency_rank": 3}, {"model": {"canonical_id": "xai/grok-build-0.1", "name": "Grok Build 0.1", "organization": {"slug": "xai", "name": "xAI", "logo_url": "https://x.ai/favicon.ico"}, "family": {"slug": "grok-build", "name": "Grok Build"}, "url": "/models/xai/grok-build-0-1"}, "efficiency_score": 62.5492, "intelligence_score": 25.0984, "affordability_score": 100.0, "estimated_output_cost_per_case": 0.00196, "intelligence_components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "grok-build-0.1", "raw_score": 71.094763, "score_unit": "percent", "relative_score": 25.0984, "weight": 1.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}], "intelligence_component_count": 1, "intelligence_component_coverage": 0.3333, "intelligence_missing_components": ["arc-agi-2", "lmarena-text"], "intelligence_coverage_status": "partial", "score_range": {"lower": 54.1831, "upper": 87.5164}, "price_source_url": "https://docs.x.ai/developers/pricing", "price_observed_at": "2026-09-03T04:30:00+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "index_version": "1.9-bdd35fc15ff7", "efficiency_rank": 4}, {"model": {"canonical_id": "openai/gpt-6.1-sol", "name": "GPT-6.1 Sol", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-6", "name": "Gpt 6"}, "url": "/models/openai/gpt-6.1-sol"}, "efficiency_score": 60.119, "intelligence_score": 85.9438, "affordability_score": 34.2942, "estimated_output_cost_per_case": 0.10375, "intelligence_components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "gpt-6.1-sol-max", "raw_score": 86.138965, "score_unit": "percent", "relative_score": 100.0, "weight": 0.333333, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "GPT-6.1 Sol (Max)", "raw_score": 94.166667, "score_unit": "percent", "relative_score": 100.0, "weight": 0.333333, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "gpt-6.1-sol-max; 95% CI [1439.17712997, 1455.81824792]; votes 5762; rank 57", "raw_score": 1447.497689, "score_unit": "rating", "relative_score": 57.8313, "weight": 0.333333, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "intelligence_component_count": 3, "intelligence_component_coverage": 1.0, "intelligence_missing_components": [], "intelligence_coverage_status": "complete", "score_range": {"lower": 60.119, "upper": 60.119}, "price_source_url": "https://developers.openai.com/api/docs/models/gpt-6.1-sol#pricing", "price_observed_at": "2026-09-29T19:07:07.591789+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "index_version": "1.9-bdd35fc15ff7", "efficiency_rank": 5}, {"model": {"canonical_id": "qwen/qwen3.8-max", "name": "Qwen3.8-Max", "organization": {"slug": "qwen", "name": "Qwen", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6215ca5692c0ecfba9186921/hrRM50-6XcdWgg2AKpENG.jpeg"}, "family": {"slug": "qwen3-8-max", "name": "Qwen3 8 Max"}, "url": "/models/qwen/qwen3-8-max"}, "efficiency_score": 58.5701, "intelligence_score": 83.3759, "affordability_score": 33.7642, "estimated_output_cost_per_case": 0.107125, "intelligence_components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "qwen3.8-max", "raw_score": 81.879613, "score_unit": "percent", "relative_score": 82.1065, "weight": 0.5, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "qwen3.8-max; 95% CI [1477.45647186, 1487.44466984]; votes 26991; rank 17", "raw_score": 1482.450571, "score_unit": "rating", "relative_score": 84.6452, "weight": 0.5, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "intelligence_component_count": 2, "intelligence_component_coverage": 0.6667, "intelligence_missing_components": ["arc-agi-2"], "intelligence_coverage_status": "partial", "score_range": {"lower": 44.6741, "upper": 61.3407}, "price_source_url": "https://api.deepinfra.com/v1/openai/models", "price_observed_at": "2026-10-19T12:23:41.821613+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "index_version": "1.9-bdd35fc15ff7", "efficiency_rank": 6}, {"model": {"canonical_id": "google-deepmind/gemini-3.8-flash", "name": "Gemini 3.8 Flash", "organization": {"slug": "google-deepmind", "name": "Google DeepMind", "logo_url": "https://storage.googleapis.com/gdm-deepmind-com-prod-public/icons/google_deepmind_48dp.svg"}, "family": {"slug": "gemini-3", "name": "Gemini 3"}, "url": "/models/google-deepmind/gemini-3-8-flash"}, "efficiency_score": 58.5276, "intelligence_score": 89.9786, "affordability_score": 27.0767, "estimated_output_cost_per_case": 0.160447, "intelligence_components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "gemini-3.8-flash-high", "raw_score": 80.854991, "score_unit": "percent", "relative_score": 76.6904, "weight": 0.333333, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "Gemini 3.8 Flash (High)", "raw_score": 89.166667, "score_unit": "percent", "relative_score": 96.1602, "weight": 0.333333, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "gemini-3.8-flash-high; 95% CI [1494.01651648, 1503.31692078]; votes 35670; rank 8", "raw_score": 1498.666719, "score_unit": "rating", "relative_score": 97.0853, "weight": 0.333333, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "intelligence_component_count": 3, "intelligence_component_coverage": 1.0, "intelligence_missing_components": [], "intelligence_coverage_status": "complete", "score_range": {"lower": 58.5276, "upper": 58.5276}, "price_source_url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.8-flash", "price_observed_at": "2026-09-02T20:39:50+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "index_version": "1.9-bdd35fc15ff7", "efficiency_rank": 7}, {"model": {"canonical_id": "google-deepmind/gemini-3.1-pro-preview", "name": "Gemini 3.1 Pro", "organization": {"slug": "google-deepmind", "name": "Google DeepMind", "logo_url": "https://storage.googleapis.com/gdm-deepmind-com-prod-public/icons/google_deepmind_48dp.svg"}, "family": {"slug": "gemini-3", "name": "Gemini 3"}, "url": "/models/google-deepmind/gemini-3-1-pro-preview"}, "efficiency_score": 54.5654, "intelligence_score": 82.0657, "affordability_score": 27.065, "estimated_output_cost_per_case": 0.16056, "intelligence_components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "gemini-3.1-pro-preview-high", "raw_score": 81.660565, "score_unit": "percent", "relative_score": 80.9486, "weight": 0.333333, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "Gemini 3.1 Pro (Preview)", "raw_score": 77.08, "score_unit": "percent", "relative_score": 82.2371, "weight": 0.333333, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "gemini-3.1-pro-preview; 95% CI [1477.36689416, 1483.27487091]; votes 126781; rank 19", "raw_score": 1480.320883, "score_unit": "rating", "relative_score": 83.0114, "weight": 0.333333, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "intelligence_component_count": 3, "intelligence_component_coverage": 1.0, "intelligence_missing_components": [], "intelligence_coverage_status": "complete", "score_range": {"lower": 54.5654, "upper": 54.5654}, "price_source_url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-pro-preview", "price_observed_at": "2026-08-29T19:00:00+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "index_version": "1.9-bdd35fc15ff7", "efficiency_rank": 8}, {"model": {"canonical_id": "anthropic/claude-opus-5-5", "name": "Claude Opus 5.5", "organization": {"slug": "anthropic", "name": "Anthropic", "logo_url": "https://platform.claude.com/favicon.ico"}, "family": {"slug": "claude-5-5", "name": "Claude 5 5"}, "url": "/models/anthropic/claude-opus-5-5"}, "efficiency_score": 53.9305, "intelligence_score": 100.0, "affordability_score": 7.8609, "estimated_output_cost_per_case": 0.5122, "intelligence_components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "claude-opus-5-5-max-effort", "raw_score": 85.941291, "score_unit": "percent", "relative_score": 100.0, "weight": 0.5, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "Claude Opus 5.5 (High)", "raw_score": 93.333333, "score_unit": "percent", "relative_score": 100.0, "weight": 0.5, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}], "intelligence_component_count": 2, "intelligence_component_coverage": 0.6667, "intelligence_missing_components": ["lmarena-text"], "intelligence_coverage_status": "partial", "score_range": {"lower": 37.2638, "upper": 53.9305}, "price_source_url": "https://platform.claude.com/docs/en/models/opus-5-5/overview#pricing", "price_observed_at": "2026-09-22T16:54:00+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "index_version": "1.9-bdd35fc15ff7", "efficiency_rank": 9}, {"model": {"canonical_id": "openai/gpt-6-luna", "name": "GPT-6 Luna", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-6", "name": "Gpt 6"}, "url": "/models/openai/gpt-6-luna"}, "efficiency_score": 52.8102, "intelligence_score": 42.2682, "affordability_score": 63.3522, "estimated_output_cost_per_case": 0.017934, "intelligence_components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "gpt-6-luna-max", "raw_score": 75.837013, "score_unit": "percent", "relative_score": 50.1657, "weight": 0.333333, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "GPT-6 Luna (Max)", "raw_score": 59.305556, "score_unit": "percent", "relative_score": 61.762, "weight": 0.333333, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "gpt-6-luna-max; 95% CI [1386.83332056, 1396.17715895]; votes 43294; rank 165", "raw_score": 1391.50524, "score_unit": "rating", "relative_score": 14.8771, "weight": 0.333333, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "intelligence_component_count": 3, "intelligence_component_coverage": 1.0, "intelligence_missing_components": [], "intelligence_coverage_status": "complete", "score_range": {"lower": 52.8102, "upper": 52.8102}, "price_source_url": "https://developers.openai.com/api/docs/models/gpt-6-luna#pricing", "price_observed_at": "2026-09-22T18:43:47+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "index_version": "1.9-bdd35fc15ff7", "efficiency_rank": 10}, {"model": {"canonical_id": "deepseek-ai/DeepSeek-V4-Pro", "name": "DeepSeek-V4-Pro", "organization": {"slug": "deepseek-ai", "name": "DeepSeek", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6538815d1bdb3c40db94fbfa/xMBly9PUMphrFVMxLX4kq.png"}, "family": {"slug": "deepseek-v4-pro", "name": "Deepseek V4 Pro"}, "url": "/models/deepseek-ai/deepseek-v4-pro"}, "efficiency_score": 51.5107, "intelligence_score": 57.9366, "affordability_score": 45.0847, "estimated_output_cost_per_case": 0.054064, "intelligence_components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "deepseek-v4-pro", "raw_score": 76.786076, "score_unit": "percent", "relative_score": 55.1823, "weight": 0.5, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "deepseek-v4-pro; 95% CI [1447.34331837, 1455.10710237]; votes 57614; rank 49", "raw_score": 1451.22521, "score_unit": "rating", "relative_score": 60.6909, "weight": 0.5, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "intelligence_component_count": 2, "intelligence_component_coverage": 0.6667, "intelligence_missing_components": ["arc-agi-2"], "intelligence_coverage_status": "partial", "score_range": {"lower": 41.8546, "upper": 58.5212}, "price_source_url": "https://openrouter.ai/api/v1/model/deepseek/deepseek-v4-pro", "price_observed_at": "2026-08-28T16:49:00+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "index_version": "1.9-bdd35fc15ff7", "efficiency_rank": 11}, {"model": {"canonical_id": "moonshotai/Kimi-K3", "name": "Kimi-K3", "organization": {"slug": "moonshotai", "name": "Moonshot AI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/641c1e77c3983aa9490f8121/X1yT2rsaIbR9cdYGEVu0X.jpeg"}, "family": {"slug": "kimi-k3", "name": "Kimi K3"}, "url": "/models/moonshotai/kimi-k3"}, "efficiency_score": 50.0745, "intelligence_score": 73.3226, "affordability_score": 26.8264, "estimated_output_cost_per_case": 0.162891, "intelligence_components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "kimi-k3", "raw_score": 81.019178, "score_unit": "percent", "relative_score": 77.5583, "weight": 0.333333, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "Kimi K3 (Max)", "raw_score": 60.416667, "score_unit": "percent", "relative_score": 63.0419, "weight": 0.333333, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "kimi-k3-max; 95% CI [1470.96951430, 1480.17280576]; votes 32036; rank 24", "raw_score": 1475.57116, "score_unit": "rating", "relative_score": 79.3677, "weight": 0.333333, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "intelligence_component_count": 3, "intelligence_component_coverage": 1.0, "intelligence_missing_components": [], "intelligence_coverage_status": "complete", "score_range": {"lower": 50.0745, "upper": 50.0745}, "price_source_url": "https://openrouter.ai/api/v1/models", "price_observed_at": "2026-10-19T12:39:09.621619+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "index_version": "1.9-bdd35fc15ff7", "efficiency_rank": 12}, {"model": {"canonical_id": "mistralai/mistral-large-4", "name": "Mistral Large 4", "organization": {"slug": "mistralai", "name": "Mistral AI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/634c17653d11eaedd88b314d/9OgyfKstSZtbmsmuG8MbU.png"}, "family": {"slug": "mistral-large-4", "name": "Mistral Large 4"}, "url": "/models/mistralai/mistral-large-4"}, "efficiency_score": 49.8851, "intelligence_score": 54.5771, "affordability_score": 45.1931, "estimated_output_cost_per_case": 0.053711, "intelligence_components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "mistral-large-4-high", "raw_score": 76.671572, "score_unit": "percent", "relative_score": 54.5771, "weight": 1.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}], "intelligence_component_count": 1, "intelligence_component_coverage": 0.3333, "intelligence_missing_components": ["arc-agi-2", "lmarena-text"], "intelligence_coverage_status": "partial", "score_range": {"lower": 31.6928, "upper": 65.0261}, "price_source_url": "https://docs.mistral.ai/inference/pricing", "price_observed_at": "2026-10-06T14:41:00+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "index_version": "1.9-bdd35fc15ff7", "efficiency_rank": 13}, {"model": {"canonical_id": "anthropic/claude-fable-5-1", "name": "Claude Fable 5.1", "organization": {"slug": "anthropic", "name": "Anthropic", "logo_url": "https://platform.claude.com/favicon.ico"}, "family": {"slug": "claude-5-1", "name": "Claude 5 1"}, "url": "/models/anthropic/claude-fable-5-1"}, "efficiency_score": 49.52, "intelligence_score": 99.04, "affordability_score": 0.0, "estimated_output_cost_per_case": 0.8235, "intelligence_components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "claude-fable-5-1-max-effort", "raw_score": 86.816836, "score_unit": "percent", "relative_score": 100.0, "weight": 0.333333, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "Claude Fable 5.1 (XHigh)", "raw_score": 90.0, "score_unit": "percent", "relative_score": 97.1201, "weight": 0.333333, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "claude-fable-5.1-max; 95% CI [1503.84123637, 1516.03584930]; votes 14121; rank 3", "raw_score": 1509.938543, "score_unit": "rating", "relative_score": 100.0, "weight": 0.333333, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "intelligence_component_count": 3, "intelligence_component_coverage": 1.0, "intelligence_missing_components": [], "intelligence_coverage_status": "complete", "score_range": {"lower": 49.52, "upper": 49.52}, "price_source_url": "https://platform.claude.com/docs/en/models/fable-5-1/overview#pricing", "price_observed_at": "2026-09-03T04:30:00+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "index_version": "1.9-bdd35fc15ff7", "efficiency_rank": 14}, {"model": {"canonical_id": "MiniMaxAI/MiniMax-M3", "name": "MiniMax-M3", "organization": {"slug": "minimaxai", "name": "MiniMax", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/676e38ad04af5bec20bc9faf/dUd-LsZEX0H_d4qefO_g6.jpeg"}, "family": {"slug": "minimax-m3", "name": "Minimax M3"}, "url": "/models/minimaxai/minimax-m3"}, "efficiency_score": 49.0103, "intelligence_score": 33.8637, "affordability_score": 64.157, "estimated_output_cost_per_case": 0.017083, "intelligence_components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "minimax-m3", "raw_score": 70.259864, "score_unit": "percent", "relative_score": 20.6852, "weight": 0.5, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "minimax-m3; 95% CI [1429.60573674, 1437.26171309]; votes 63129; rank 91", "raw_score": 1433.433725, "score_unit": "rating", "relative_score": 47.0422, "weight": 0.5, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "intelligence_component_count": 2, "intelligence_component_coverage": 0.6667, "intelligence_missing_components": ["arc-agi-2"], "intelligence_coverage_status": "partial", "score_range": {"lower": 43.3664, "upper": 60.033}, "price_source_url": "https://api.deepinfra.com/v1/openai/models", "price_observed_at": "2026-10-19T12:23:41.821613+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "index_version": "1.9-bdd35fc15ff7", "efficiency_rank": 15}, {"model": {"canonical_id": "openai/gpt-5.6-terra", "name": "GPT-5.6 Terra", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-5-6", "name": "Gpt 5 6"}, "url": "/models/openai/gpt-5-6-terra"}, "efficiency_score": 47.9996, "intelligence_score": 77.2752, "affordability_score": 18.724, "estimated_output_cost_per_case": 0.26574, "intelligence_components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "gpt-5.6-terra-max", "raw_score": 82.314061, "score_unit": "percent", "relative_score": 84.403, "weight": 0.333333, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "GPT-5.6 Terra (Max)", "raw_score": 83.9, "score_unit": "percent", "relative_score": 90.0933, "weight": 0.333333, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "gpt-5.6-terra-xhigh; 95% CI [1442.59739772, 1451.08894108]; votes 42358; rank 59", "raw_score": 1446.843169, "score_unit": "rating", "relative_score": 57.3292, "weight": 0.333333, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "intelligence_component_count": 3, "intelligence_component_coverage": 1.0, "intelligence_missing_components": [], "intelligence_coverage_status": "complete", "score_range": {"lower": 47.9996, "upper": 47.9996}, "price_source_url": "https://developers.openai.com/api/docs/models/gpt-5.6-terra", "price_observed_at": "2026-09-03T04:30:00+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "index_version": "1.9-bdd35fc15ff7", "efficiency_rank": 16}, {"model": {"canonical_id": "Qwen/Qwen3.8-27B", "name": "Qwen3.8-27B", "organization": {"slug": "qwen", "name": "Qwen", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/6215ca5692c0ecfba9186921/hrRM50-6XcdWgg2AKpENG.jpeg"}, "family": {"slug": "qwen3-8-27b", "name": "Qwen3 8 27b"}, "url": "/models/qwen/qwen3-8-27b"}, "efficiency_score": 47.3266, "intelligence_score": 52.1606, "affordability_score": 42.4926, "estimated_output_cost_per_case": 0.063228, "intelligence_components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "qwen3.8-27b", "raw_score": 78.024105, "score_unit": "percent", "relative_score": 61.7265, "weight": 0.333333, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "Qwen3.8-27B (XHigh)", "raw_score": 42.361111, "score_unit": "percent", "relative_score": 42.243, "weight": 0.333333, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "qwen3.8-27b; 95% CI [1435.44919577, 1445.67962049]; votes 22539; rank 74", "raw_score": 1440.564408, "score_unit": "rating", "relative_score": 52.5125, "weight": 0.333333, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "intelligence_component_count": 3, "intelligence_component_coverage": 1.0, "intelligence_missing_components": [], "intelligence_coverage_status": "complete", "score_range": {"lower": 47.3266, "upper": 47.3266}, "price_source_url": "https://openrouter.ai/api/v1/models", "price_observed_at": "2026-10-19T12:39:09.621619+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "index_version": "1.9-bdd35fc15ff7", "efficiency_rank": 17}, {"model": {"canonical_id": "openai/gpt-6-astra", "name": "GPT-6 Astra", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-6", "name": "Gpt 6"}, "url": "/models/openai/gpt-6-astra"}, "efficiency_score": 46.0765, "intelligence_score": 84.5535, "affordability_score": 7.5996, "estimated_output_cost_per_case": 0.52035, "intelligence_components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "gpt-6-astra-max", "raw_score": 86.47107, "score_unit": "percent", "relative_score": 100.0, "weight": 0.333333, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "GPT-6 Astra (Max)", "raw_score": 95.0, "score_unit": "percent", "relative_score": 100.0, "weight": 0.333333, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "gpt-6-astra-max; 95% CI [1435.67981608, 1448.44185822]; votes 11674; rank 72", "raw_score": 1442.060837, "score_unit": "rating", "relative_score": 53.6605, "weight": 0.333333, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "intelligence_component_count": 3, "intelligence_component_coverage": 1.0, "intelligence_missing_components": [], "intelligence_coverage_status": "complete", "score_range": {"lower": 46.0765, "upper": 46.0765}, "price_source_url": "https://developers.openai.com/api/docs/models/gpt-6-astra#pricing", "price_observed_at": "2026-09-04T05:43:28+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "index_version": "1.9-bdd35fc15ff7", "efficiency_rank": 18}, {"model": {"canonical_id": "zai-org/glm-5.3", "name": "GLM-5.3", "organization": {"slug": "zai-org", "name": "Z.ai", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/62dc173789b4cf157d36ebee/i_pxzM2ZDo3Ub-BEgIkE9.png"}, "family": {"slug": "glm-5-3", "name": "Glm 5 3"}, "url": "/models/zai-org/glm-5-3"}, "efficiency_score": 45.8761, "intelligence_score": 71.9085, "affordability_score": 19.8437, "estimated_output_cost_per_case": 0.24836, "intelligence_components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "glm-5.3", "raw_score": 79.146315, "score_unit": "percent", "relative_score": 67.6584, "weight": 0.5, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "glm-5.3-max; 95% CI [1466.15226961, 1476.62346864]; votes 21797; rank 27", "raw_score": 1471.387869, "score_unit": "rating", "relative_score": 76.1585, "weight": 0.5, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "intelligence_component_count": 2, "intelligence_component_coverage": 0.6667, "intelligence_missing_components": ["arc-agi-2"], "intelligence_coverage_status": "partial", "score_range": {"lower": 33.8914, "upper": 50.558}, "price_source_url": "https://api.deepinfra.com/v1/openai/models", "price_observed_at": "2026-10-19T12:23:41.821613+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "index_version": "1.9-bdd35fc15ff7", "efficiency_rank": 19}, {"model": {"canonical_id": "xai/grok-4.7", "name": "Grok 4.7", "organization": {"slug": "xai", "name": "xAI", "logo_url": "https://x.ai/favicon.ico"}, "family": {"slug": "grok-4", "name": "Grok 4"}, "url": "/models/xai/grok-4-7"}, "efficiency_score": 44.3012, "intelligence_score": 73.9898, "affordability_score": 14.6126, "estimated_output_cost_per_case": 0.340656, "intelligence_components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "grok-4.7-xhigh", "raw_score": 82.203353, "score_unit": "percent", "relative_score": 83.8178, "weight": 0.5, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "Grok 4.7 (XHigh)", "raw_score": 61.388889, "score_unit": "percent", "relative_score": 64.1618, "weight": 0.5, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}], "intelligence_component_count": 2, "intelligence_component_coverage": 0.6667, "intelligence_missing_components": ["lmarena-text"], "intelligence_coverage_status": "partial", "score_range": {"lower": 31.9695, "upper": 48.6362}, "price_source_url": "https://docs.x.ai/developers/models/grok-4.7#pricing", "price_observed_at": "2026-09-22T06:25:00+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "index_version": "1.9-bdd35fc15ff7", "efficiency_rank": 20}, {"model": {"canonical_id": "anthropic/claude-sonnet-5", "name": "Claude Sonnet 5", "organization": {"slug": "anthropic", "name": "Anthropic", "logo_url": "https://platform.claude.com/favicon.ico"}, "family": {"slug": "claude-5", "name": "Claude 5"}, "url": "/models/anthropic/claude-sonnet-5"}, "efficiency_score": 43.4946, "intelligence_score": 63.08, "affordability_score": 23.9092, "estimated_output_cost_per_case": 0.19428, "intelligence_components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "claude-sonnet-5-xhigh-effort", "raw_score": 80.014756, "score_unit": "percent", "relative_score": 72.249, "weight": 0.5, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "claude-sonnet-5-high; 95% CI [1438.26387267, 1446.51078670]; votes 48998; rank 71", "raw_score": 1442.38733, "score_unit": "rating", "relative_score": 53.9109, "weight": 0.5, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "intelligence_component_count": 2, "intelligence_component_coverage": 0.6667, "intelligence_missing_components": ["arc-agi-2"], "intelligence_coverage_status": "partial", "score_range": {"lower": 32.9812, "upper": 49.6479}, "price_source_url": "https://platform.claude.com/docs/en/models/overview", "price_observed_at": "2026-09-03T04:30:00+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "index_version": "1.9-bdd35fc15ff7", "efficiency_rank": 21}, {"model": {"canonical_id": "thinkingmachines/Inkling", "name": "Inkling", "organization": {"slug": "thinkingmachines", "name": "Thinking Machines Lab", "logo_url": "https://thinkingmachines.ai/images/apple-touch-icon.png"}, "family": {"slug": "inkling", "name": "Inkling"}, "url": "/models/thinkingmachines/inkling"}, "efficiency_score": 42.0037, "intelligence_score": 47.3527, "affordability_score": 36.6546, "estimated_output_cost_per_case": 0.089963, "intelligence_components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "inkling-xhigh", "raw_score": 76.470779, "score_unit": "percent", "relative_score": 53.5157, "weight": 0.333333, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "Inkling", "raw_score": 36.527778, "score_unit": "percent", "relative_score": 35.5233, "weight": 0.333333, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "inkling; 95% CI [1436.89849760, 1445.55102061]; votes 39763; rank 73", "raw_score": 1441.224759, "score_unit": "rating", "relative_score": 53.0191, "weight": 0.333333, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "intelligence_component_count": 3, "intelligence_component_coverage": 1.0, "intelligence_missing_components": [], "intelligence_coverage_status": "complete", "score_range": {"lower": 42.0037, "upper": 42.0037}, "price_source_url": "https://api.deepinfra.com/v1/openai/models", "price_observed_at": "2026-10-15T08:23:35.581686+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "index_version": "1.9-bdd35fc15ff7", "efficiency_rank": 22}, {"model": {"canonical_id": "moonshotai/Kimi-K2.7-Code", "name": "Kimi K2.7 Code", "organization": {"slug": "moonshotai", "name": "Moonshot AI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/641c1e77c3983aa9490f8121/X1yT2rsaIbR9cdYGEVu0X.jpeg"}, "family": {"slug": "kimi-k2-7", "name": "Kimi K2 7"}, "url": "/models/moonshotai/kimi-k2-7-code"}, "efficiency_score": 37.8094, "intelligence_score": 26.9627, "affordability_score": 48.656, "estimated_output_cost_per_case": 0.043573, "intelligence_components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "kimi-k2.7-code", "raw_score": 71.447447, "score_unit": "percent", "relative_score": 26.9627, "weight": 1.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}], "intelligence_component_count": 1, "intelligence_component_coverage": 0.3333, "intelligence_missing_components": ["arc-agi-2", "lmarena-text"], "intelligence_coverage_status": "partial", "score_range": {"lower": 28.8218, "upper": 62.1551}, "price_source_url": "https://openrouter.ai/api/v1/models", "price_observed_at": "2026-10-19T12:39:09.621619+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "index_version": "1.9-bdd35fc15ff7", "efficiency_rank": 23}, {"model": {"canonical_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", "name": "NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", "organization": {"slug": "nvidia", "name": "NVIDIA", "logo_url": "https://www.nvidia.com/etc/designs/nvidiaGDC/clientlibs_base/images/NVIDIA-Logo.svg"}, "family": {"slug": "nvidia-nemotron-3-ultra-550b-a55b-bf16", "name": "Nvidia Nemotron 3 Ultra 550b A55b Bf16"}, "url": "/models/nvidia/nvidia-nemotron-3-ultra-550b-a55b-bf16"}, "efficiency_score": 37.0595, "intelligence_score": 37.77, "affordability_score": 36.349, "estimated_output_cost_per_case": 0.091639, "intelligence_components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "nemotron-3-ultra-550b-a55b", "raw_score": 73.491995, "score_unit": "percent", "relative_score": 37.77, "weight": 1.0, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}], "intelligence_component_count": 1, "intelligence_component_coverage": 0.3333, "intelligence_missing_components": ["arc-agi-2", "lmarena-text"], "intelligence_coverage_status": "partial", "score_range": {"lower": 24.4695, "upper": 57.8029}, "price_source_url": "https://openrouter.ai/api/v1/model/nvidia/nemotron-3-ultra-550b-a55b", "price_observed_at": "2026-08-29T04:33:54+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "index_version": "1.9-bdd35fc15ff7", "efficiency_rank": 24}, {"model": {"canonical_id": "google-deepmind/gemini-3.5-flash-lite", "name": "Gemini 3.5 Flash-Lite", "organization": {"slug": "google-deepmind", "name": "Google DeepMind", "logo_url": "https://storage.googleapis.com/gdm-deepmind-com-prod-public/icons/google_deepmind_48dp.svg"}, "family": {"slug": "gemini-3", "name": "Gemini 3"}, "url": "/models/google-deepmind/gemini-3-5-flash-lite"}, "efficiency_score": 36.6374, "intelligence_score": 17.7728, "affordability_score": 55.5021, "estimated_output_cost_per_case": 0.028815, "intelligence_components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "gemini-3.5-flash-lite-high", "raw_score": 66.346626, "score_unit": "percent", "relative_score": 0.0, "weight": 0.333333, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "Gemini 3.5 Flash-Lite (High)", "raw_score": 10.277778, "score_unit": "percent", "relative_score": 5.2848, "weight": 0.333333, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "gemini-3.5-flash-lite; 95% CI [1430.26500547, 1439.18690077]; votes 35845; rank 88", "raw_score": 1434.725953, "score_unit": "rating", "relative_score": 48.0336, "weight": 0.333333, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "intelligence_component_count": 3, "intelligence_component_coverage": 1.0, "intelligence_missing_components": [], "intelligence_coverage_status": "complete", "score_range": {"lower": 36.6374, "upper": 36.6374}, "price_source_url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.5-flash-lite", "price_observed_at": "2026-08-29T19:00:00+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "index_version": "1.9-bdd35fc15ff7", "efficiency_rank": 25}, {"model": {"canonical_id": "openai/gpt-5.4-nano", "name": "GPT-5.4 Nano", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-5-4", "name": "Gpt 5 4"}, "url": "/models/openai/gpt-5-4-nano"}, "efficiency_score": 29.8583, "intelligence_score": 15.7163, "affordability_score": 44.0003, "estimated_output_cost_per_case": 0.057724, "intelligence_components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "gpt-5.4-nano-xhigh", "raw_score": 75.266301, "score_unit": "percent", "relative_score": 47.1489, "weight": 0.333333, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "GPT-5.4 Nano (XHigh)", "raw_score": 5.69, "score_unit": "percent", "relative_score": 0.0, "weight": 0.333333, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "gpt-5.4-nano-high; 95% CI [1368.35606198, 1375.86886621]; votes 62426; rank 181", "raw_score": 1372.112464, "score_unit": "rating", "relative_score": 0.0, "weight": 0.333333, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "intelligence_component_count": 3, "intelligence_component_coverage": 1.0, "intelligence_missing_components": [], "intelligence_coverage_status": "complete", "score_range": {"lower": 29.8583, "upper": 29.8583}, "price_source_url": "https://developers.openai.com/api/docs/models/gpt-5.4-nano#pricing", "price_observed_at": "2026-09-03T04:30:00+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "index_version": "1.9-bdd35fc15ff7", "efficiency_rank": 26}, {"model": {"canonical_id": "openai/gpt-5.4-mini", "name": "GPT-5.4 Mini", "organization": {"slug": "openai", "name": "OpenAI", "logo_url": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png"}, "family": {"slug": "gpt-5-4", "name": "Gpt 5 4"}, "url": "/models/openai/gpt-5-4-mini"}, "efficiency_score": 21.5608, "intelligence_score": 20.7753, "affordability_score": 22.3462, "estimated_output_cost_per_case": 0.213516, "intelligence_components": [{"benchmark": "livebench", "publisher": "LiveBench", "benchmark_version": "2026-06-25-90f8d44da965", "configuration": "gpt-5.4-mini-xhigh", "raw_score": 69.530263, "score_unit": "percent", "relative_score": 16.8285, "weight": 0.333333, "source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv"}, {"benchmark": "arc-agi-2", "publisher": "ARC Prize Foundation", "benchmark_version": "verified-v2-4c23aeea7233", "configuration": "GPT-5.4 Mini (XHigh)", "raw_score": 18.9, "score_unit": "percent", "relative_score": 15.2171, "weight": 0.333333, "source_url": "https://arcprize.org/media/data/leaderboard/v2.json#sha256=4c23aeea72335c4e9b32e4ddaad405a96901bcf19370ede4cd05f8d7675cabee"}, {"benchmark": "lmarena-text", "publisher": "LMArena", "benchmark_version": "text-2026-10-13-4589dee83b59", "configuration": "gpt-5.4-mini-high; 95% CI [1407.86458416, 1415.30312295]; votes 63461; rank 137", "raw_score": 1411.583854, "score_unit": "rating", "relative_score": 30.2802, "weight": 0.333333, "source_url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/4589dee83b594891961ae5190c508a9288d2c2ae/text/latest-00000-of-00001.parquet#sha256=e8a6046e38590ea329858fd4f425b9dfc4e8ba1db5a8d2fd8a60d131762a57f0"}], "intelligence_component_count": 3, "intelligence_component_coverage": 1.0, "intelligence_missing_components": [], "intelligence_coverage_status": "complete", "score_range": {"lower": 21.5608, "upper": 21.5608}, "price_source_url": "https://developers.openai.com/api/docs/models/gpt-5.4-mini#pricing", "price_observed_at": "2026-09-03T04:30:00+00:00", "benchmark_source_url": "https://github.com/LiveBench/new-livebench/blob/90f8d44da9650d4bf4a8454157947d7b8432551e/public/table_2026_06_25.csv", "benchmark_observed_at": "2026-10-15T12:46:28.151878+00:00", "index_version": "1.9-bdd35fc15ff7", "efficiency_rank": 27}], "value_efficiency_index": {"name": "MM Intelligence-Cost Efficiency", "short_name": "MM Efficiency", "method_version": "1.9", "version": "1.9-bdd35fc15ff7", "profile": "relative intelligence and output-cost balance", "status": "ready", "method": "Equal-weight mean of MM Relative Intelligence and logarithmically normalized affordability within the current available common cohort; Intelligence may use a labeled one- or two-of-three provisional core.", "intelligence_index_version": "4.4", "cost_measure": "Estimated USD output cost per published LiveBench case", "cost_normalization": "Logarithmic min-max affordability; the lowest eligible cost scores 100 and the highest scores 0; identical costs all score 50.", "weights": {"intelligence": 0.5, "affordability": 0.5}, "eligible_model_count": 27, "reference_cohort": ["MiniMaxAI/MiniMax-M3", "Qwen/Qwen3.8-27B", "anthropic/claude-fable-5-1", "anthropic/claude-opus-5-5", "anthropic/claude-sonnet-5", "deepseek-ai/DeepSeek-V4-Pro", "deepseek-ai/DeepSeek-V4.1-Flash", "google-deepmind/gemini-3.1-pro-preview", "google-deepmind/gemini-3.5-flash-lite", "google-deepmind/gemini-3.8-flash", "mistralai/mistral-large-4", "moonshotai/Kimi-K2.7-Code", "moonshotai/Kimi-K3", "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", "openai/gpt-5.4-mini", "openai/gpt-5.4-nano", "openai/gpt-5.6-terra", "openai/gpt-6-astra", "openai/gpt-6-luna", "openai/gpt-6.1-sol", "qwen/qwen3.8-flash", "qwen/qwen3.8-max", "thinkingmachines/Inkling", "xai/grok-4.7", "xai/grok-build-0.1", "zai-org/glm-5.3", "zai-org/glm-5.3-flash"], "input_snapshot": "bdd35fc15ff732dc24854ec2e30eb83caeebbffbd8ce788840490cc33e434bf7"}, "methodology": {"evidence_class": "third_party_benchmark", "verification": "Only exact results from original-publisher artifacts are eligible; scores are independently recomputed when the publisher exposes sufficient inputs.", "run_selection": "For each model and benchmark, select the published run with the highest output-token spend; use the latest result only when token accounting is unavailable.", "intelligence": "MM Relative Intelligence Index v4.4 is the equal-weight mean of available LiveBench, ARC-AGI-2, and LMArena Text scores linearly normalized to the frozen 20-model reference range. LMArena Text is human preference, not objective task success. At least one original-publisher result is required; one- and two-source rows are provisional with full-core coverage bounds, not statistical confidence intervals. Default ranks include reviewed current product-line generations only; predecessor evidence remains on model and benchmark pages. Equal published scores share ranks; scores from different index versions are not comparable.", "performance": "Each benchmark leader is set to 100. A model earns weighted points from every benchmark where it has a verified result; missing benchmarks earn no points, and the total produces one overall rank.", "efficiency": "Within each token-accounted benchmark, performance points per 1,000 output tokens are scored relative to the most efficient eligible run. Missing token-accounted benchmarks earn no points, and the total produces one overall rank.", "frontier": "The graph uses the benchmark with the strongest configuration coverage and includes every published configuration. Highlighted points are not dominated on both benchmark performance and actual output-token spend.", "quality_cost": "LiveBench quality is compared with estimated output cost using the lowest currently published USD output-token rate for each model. Score-adjusted output cost divides the estimated output cost for one published benchmark case by the model's LiveBench score as a fraction of 100. It is an estimate from published price and token artifacts, not an invoice or a task success rate.", "value_efficiency": "MM Intelligence-Cost Efficiency is the equal-weight mean of the MM Relative Intelligence score and logarithmically normalized affordability across the current available cohort with both intelligence and estimated LiveBench output-cost evidence. Provisional Intelligence bounds propagate through the 50/50 mean. Equal costs receive neutral affordability 50. Scores compare only within the published input snapshot.", "missing_data": "Missing benchmarks are never estimated. Intelligence averages available observed core inputs, requiring at least one, and publishes full-core coverage bounds. Legacy broad coverage points use a fixed denominator and are not capability scores."}, "updated_at": "2026-10-19T03:46:38.481610+00:00", "eligible_result_count": 208, "frontier_scope": "tonebench", "quality_cost_scope": "livebench", "published_weight": 11.0, "selected_weight": 208.0}, "meta": {"dataset_status": "live", "is_live": true, "disclaimer": null}}