Benchmark By Score Rank
Overall 1
AA Intelligence Index4.3.2 AA Intelligence Index 4.3.2: Artificial Analysis combines tests of knowledge, reasoning, coding and tool use into one score AA 26.1 #75 of 334
Knowledge 19
Arena Text Arena Text · overall: Human pairwise preferences in the stated text vote pool Arena 1,465 #36 of 196+12 versions & slices English Arena Text · english: Human pairwise preferences in the stated text vote pool Arena 1,475 #23 of 188instruction following Arena Text · instruction following: Human pairwise preferences in the stated text vote pool Arena 1,452 #35 of 188non-English Arena Text · non english: Human pairwise preferences in the stated text vote pool Arena 1,448 #31 of 188overall · full cohort Arena Text · overall · snapshot 2026-10-15 · native board settings: Human pairwise preferences in the stated text vote pool Arena 1,462 #28 of 188Russian Arena Text · russian: Human pairwise preferences in the stated text vote pool Arena 1,454 #32 of 186Chinese Arena Text · chinese: Human pairwise preferences in the stated text vote pool Arena 1,514 #26 of 181Spanish Arena Text · spanish: Human pairwise preferences in the stated text vote pool Arena 1,469 #21 of 155German Arena Text · german: Human pairwise preferences in the stated text vote pool Arena 1,467 #24 of 154French Arena Text · french: Human pairwise preferences in the stated text vote pool Arena 1,472 #30 of 149Korean Arena Text · korean: Human pairwise preferences in the stated text vote pool Arena 1,422 #29 of 144Japanese Arena Text · japanese: Human pairwise preferences in the stated text vote pool Arena 1,436 #25 of 138Polish Arena Text · polish: Human pairwise preferences in the stated text vote pool Arena 1,447 #30 of 133
AA Omniscience Index AA Omniscience Index: Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA 0.9 #65 of 318
SimpleQA Verifiedv1 SimpleQA Verified v1: Accuracy on short factual questions with verified answers, answered without web access 34% #51 of 83
AA OmniscienceAccuracy AA Omniscience · Accuracy: Measures correct answers on the AA Omniscience factual knowledge test AA 23.7% #124 of 318+1 versions & slices Hallucination Rate AA Omniscience · Hallucination Rate: Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test AA 29.9% #34 of 318
IFBench (instructions) IFBench (instructions): Checks whether the model follows precise formatting and content instructions AA 76.3% #14 of 245
EQ-Bench3 EQ-Bench 3: Judge-rated responses to social and emotionally nuanced scenarios, scored through the source pairwise ranking EQ-Bench 1,567 #10 of 50
Reasoning 1
Chess Puzzles Chess Puzzles: Models choose the best next move from a novel chess position Epoch 20% #54 of 68
Math 18
FrontierMath Tiers 1–3 (v2) FrontierMath Tiers 1–3 (v2): Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 36.8% #52 of 69
FrontierMath FrontierMath: Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 33.4% #11 of 40
MathArenaApex MathArena · apex · Apex: Answer accuracy on the named mathematics competition under the recorded effort MathArena 11.5% #17 of 34+14 versions & slices Apex Shortlist MathArena · apex · Apex Shortlist: Answer accuracy on the named mathematics competition under the recorded effort MathArena 71.8% #12 of 30AIME 2026 MathArena · AIME 2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 95.8% #12 of 24HMMT February 2026 MathArena · HMMT February 2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 89.4% #13 of 24ArXivMath · February 2026 MathArena · arxiv · 02/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 39.1% #13 of 20ArXivMath · May 2026 MathArena · arxiv · 05/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 52.5% #16 of 19ArXivMath · January 2026 MathArena · arxiv · 01/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 65.2% #8 of 18BrokenArXiv · May 2026 MathArena · arxiv_false · 05/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 10% #16 of 18ArXivMath · April 2026 MathArena · arxiv · 04/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 36.3% #15 of 17BrokenArXiv · April 2026 MathArena · arxiv_false · 04/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 8.2% #14 of 15BrokenArXiv · February 2026 MathArena · arxiv_false · 02/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 9.3% #12 of 15ArXivMath · March 2026 MathArena · arxiv · 03/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 49.2% #11 of 14BrokenArXiv · March 2026 MathArena · arxiv_false · 03/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 6.5% #11 of 13Project Euler MathArena · euler · Project Euler: Answer accuracy on the named mathematics competition under the recorded effort MathArena 67.2% #5 of 11ArXivLean · March 2026 MathArena · arxivlean · 03/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 2.4% #5 of 5
FrontierMath Tier4 FrontierMath Tier 4: Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 12.5% #10 of 33
Science 2
Humanity's Last Exam Humanity's Last Exam: Very hard expert questions across many fields, written to stump today’s models AA 30.1% #80 of 334
CritPt (physics) CritPt (physics): Research-level physics problems that need many careful reasoning steps AA 4.6% #81 of 321
Health & law 4
Vals LegalBench Vals LegalBench: Legal reasoning and legal-language understanding on LegalBench Vals 84.4% #29 of 89
Vals MedScribe Vals MedScribe: Accuracy of clinical notes produced from consultation transcripts Vals 72.3% #66 of 80
Vals MedCode Vals MedCode: Medical coding accuracy on patient encounters Vals 41.6% #44 of 78
Vals Legal Research Bench Vals Legal Research Bench: Grounded legal research; a task passes only if all criteria pass Vals 27.9% #44 of 69
Documents 2
AA-LCR (long context)1.1 AA-LCR (long context) 1.1: Questions that need reading and connecting facts across very long documents (around 100K tokens) AA 73.7% #97 of 273
GDP.pdfAA all-pass GDP.pdf · AA all-pass: Models reason over professional PDF documents; an attempt passes only when every atomic criterion passes 8.4% #66 of 133
Legacy · saturated or no longer reported 3
GPQA Diamond GPQA Diamond: Graduate-level biology, chemistry and physics questions that can’t be solved by a quick web search 86.8% #61 of 312+1 versions & slices Epoch GPQA Diamond · source setting 2: Models answer graduate-level science multiple-choice questions Epoch 89.9% #34 of 133
OTIS Mock AIME 20242025 OTIS Mock AIME 2024 2025: Models solve the stated OTIS mock AIME mathematics problems Epoch 93.3% #38 of 130
No benchmark matches
CheaperGemini 3.8 Flashunstated×2.2-30%*$0.75 / $3.75Sampling parameters are ignored+1
BetterGPT-6 Lunamax+22%-91%$0.068Function calling only with none · Chat Completions+3
OpenDeepSeek V4 Pro 0813max+56%-8%$0.67Memory (4-bit): 452 GB → 990 GB+5
Muse Spark 1.2xhigh+77%-7%$0.97Only auto tool_choice is supported+1
Grok 4.5high+42%+40%$0.88
Qwen3 235B A22B Thinking 2507unstatedOpen+19%-65%$0.23 / $2.30No strict JSONTInklingxhighOpen+19%-20%$0.95 / $4.05Memory (4-bit): 452 GB → 571 GB+1
Kimi K2.7 CodeunstatedOpen+7%-20%$0.95 / $4Memory (4-bit): 452 GB → 616 GB+1