Benchmark By Score Rank
Overall 1
AA Intelligence Index4.3.2 Artificial Analysis combines tests of knowledge, reasoning, coding and tool use into one score AA 49.6 #10 of 336
Knowledge 21 Leads on 1
Arena TextEnglish Human pairwise preferences in the stated text vote pool Arena 1,498 #9 of 205+13 versions & slices instruction following Human pairwise preferences in the stated text vote pool Arena 1,502 #6 of 205non-English Human pairwise preferences in the stated text vote pool Arena 1,481 #9 of 205Russian Human pairwise preferences in the stated text vote pool Arena 1,503 #7 of 203Chinese Human pairwise preferences in the stated text vote pool Arena 1,544 #7 of 198overall · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,491 #10 of 198overall Human pairwise preferences in the stated text vote pool Arena 1,504 #4 of 196overall · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,491 #8 of 188Spanish Human pairwise preferences in the stated text vote pool Arena 1,495 #6 of 168German Human pairwise preferences in the stated text vote pool Arena 1,485 #13 of 167French Human pairwise preferences in the stated text vote pool Arena 1,506 #7 of 164Korean Human pairwise preferences in the stated text vote pool Arena 1,488 #4 of 156Japanese Human pairwise preferences in the stated text vote pool Arena 1,506 #5 of 152Polish Human pairwise preferences in the stated text vote pool Arena 1,490 #9 of 142
AA Omniscience Index Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA 43.3 #4 of 320
SimpleQA Verifiedv1 Accuracy on short factual questions with verified answers, answered without web access 70.7% #8 of 84
AA OmniscienceAccuracy Measures correct answers on the AA Omniscience factual knowledge test AA 65.4% #3 of 320+1 versions & slices Hallucination Rate Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test AA 63.6% #117 of 320
IFBench (instructions) Checks whether the model follows precise formatting and content instructions AA 63.5% #75 of 245
Mystery Game Puzzles Models choose the best move in puzzle positions from an undisclosed game Epoch 52% #11 of 65
EQ-Bench3 Judge-rated responses to social and emotionally nuanced scenarios, scored through the source pairwise ranking EQ-Bench 2,096 #1 of 53
Reasoning 5 Leads on 1
ARC-AGI-2semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 88.3% #10 of 69+1 versions & slices public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 93.3% #8 of 66
Chess Puzzles Models choose the best next move from a novel chess position Epoch 47% #19 of 69
ARC-AGI-1semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 98.5% #1 of 67+1 versions & slices public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 97.9% #13 of 64
Math 10
FrontierMath Tiers 1–3 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 87% #9 of 70
FrontierMath Tier 4 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 90.2% #4 of 55
MathArenaArXivMath · June 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 85.4% #6 of 24+6 versions & slices BrokenArXiv · June 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 47.8% #13 of 24ArXivMath · May 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 87.5% #4 of 19BrokenArXiv · May 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 44.5% #7 of 18ArXivMath · April 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 72.5% #3 of 17BrokenArXiv · April 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 54.1% #4 of 15ArXivLean · June 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 15.2% #6 of 9
FrontierMath Erdos Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 0% #6 of 13
Science 2
Humanity's Last Exam Very hard expert questions across many fields, written to stump today’s models AA 55.5% #4 of 336
CritPt (physics) Research-level physics problems that need many careful reasoning steps AA 28.6% #13 of 323
Health & law 5 Leads on 1
MLCR-AA Models synthesize long medical records; the headline credits concise answers judged both accurate and complete AA 20.6% #19 of 103
Vals LegalBench Legal reasoning and legal-language understanding on LegalBench Vals 88.6% #1 of 89
Vals MedScribe Accuracy of clinical notes produced from consultation transcripts Vals 88.5% #11 of 80
Vals MedCode Medical coding accuracy on patient encounters Vals 56.1% #4 of 78
Vals Legal Research Bench Grounded legal research; a task passes only if all criteria pass Vals 49.5% #6 of 73
Documents 2
AA-LCR (long context)1.1 Questions that need reading and connecting facts across very long documents (around 100K tokens) AA 82.3% #27 of 314
GDP.pdfAA all-pass Models reason over professional PDF documents; an attempt passes only when every atomic criterion passes 24% #13 of 135
Legacy · saturated or no longer reported 3
GPQA Diamond Graduate-level biology, chemistry and physics questions that can’t be solved by a quick web search 92.6% #17 of 312+1 versions & slices Epoch Models answer graduate-level science multiple-choice questions Epoch 85.9% #54 of 134
OTIS Mock AIME 20242025 Models solve the stated OTIS mock AIME mathematics problems Epoch 100% #1 of 131
No benchmark matches