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 38.8 #37 of 336
Knowledge 18
Arena TextEnglish Human pairwise preferences in the stated text vote pool Arena 1,453 #43 of 205+13 versions & slices instruction following Human pairwise preferences in the stated text vote pool Arena 1,445 #39 of 205non-English Human pairwise preferences in the stated text vote pool Arena 1,440 #36 of 205Russian Human pairwise preferences in the stated text vote pool Arena 1,449 #37 of 203Chinese Human pairwise preferences in the stated text vote pool Arena 1,494 #43 of 198overall · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,448 #39 of 198overall Human pairwise preferences in the stated text vote pool Arena 1,466 #34 of 196overall · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,448 #38 of 188Spanish Human pairwise preferences in the stated text vote pool Arena 1,451 #44 of 168German Human pairwise preferences in the stated text vote pool Arena 1,448 #39 of 167French Human pairwise preferences in the stated text vote pool Arena 1,457 #51 of 164Korean Human pairwise preferences in the stated text vote pool Arena 1,402 #42 of 156Japanese Human pairwise preferences in the stated text vote pool Arena 1,431 #29 of 152Polish Human pairwise preferences in the stated text vote pool Arena 1,431 #50 of 142
AA Omniscience Index Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA 25.3 #21 of 320
SimpleQA Verifiedv1 Accuracy on short factual questions with verified answers, answered without web access 53.8% #20 of 84
AA OmniscienceAccuracy Measures correct answers on the AA Omniscience factual knowledge test AA 51.6% #17 of 320+1 versions & slices Hallucination Rate Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test AA 54.1% #99 of 320
Reasoning 6
ARC-AGI-2semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 52.6% #36 of 69+1 versions & slices public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 57.5% #31 of 66
Chess Puzzles Models choose the best next move from a novel chess position Epoch 35% #39 of 69
ARC-AGI-1semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 87.2% #33 of 67+1 versions & slices public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 92.5% #29 of 64
ARC-AGI-3semi-private Measures interactive game solving through relative human action efficiency ARC 0.3% #16 of 19
Math 4
FrontierMath Tiers 1–3 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 57.2% #39 of 70
FrontierMath Tier 4 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 24.4% #38 of 55
MathArenaArXivMath · June 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 66.7% #16 of 24+1 versions & slices BrokenArXiv · June 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 29.3% #16 of 24
Science 2
Humanity's Last Exam Very hard expert questions across many fields, written to stump today’s models AA 42.7% #35 of 336
CritPt (physics) Research-level physics problems that need many careful reasoning steps AA 15.4% #45 of 323
Health & law 5
MLCR-AA Models synthesize long medical records; the headline credits concise answers judged both accurate and complete AA 16.1% #34 of 103
Vals LegalBench Legal reasoning and legal-language understanding on LegalBench Vals 86% #15 of 89
Vals MedScribe Accuracy of clinical notes produced from consultation transcripts Vals 86.9% #18 of 80
Vals MedCode Medical coding accuracy on patient encounters Vals 43.3% #38 of 78
Vals Legal Research Bench Grounded legal research; a task passes only if all criteria pass Vals 38% #33 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 79.3% #55 of 314
GDP.pdfAA all-pass Models reason over professional PDF documents; an attempt passes only when every atomic criterion passes 18.8% #28 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 93.1% #12 of 312+1 versions & slices Epoch Models answer graduate-level science multiple-choice questions Epoch 93.4% #13 of 134
OTIS Mock AIME 20242025 Models solve the stated OTIS mock AIME mathematics problems Epoch 97.8% #27 of 131
No benchmark matches