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 33.5 #51 of 336
Knowledge 20
Arena TextEnglish Human pairwise preferences in the stated text vote pool Arena 1,458 #37 of 205+13 versions & slices instruction following Human pairwise preferences in the stated text vote pool Arena 1,483 #13 of 205non-English Human pairwise preferences in the stated text vote pool Arena 1,451 #28 of 205Russian Human pairwise preferences in the stated text vote pool Arena 1,472 #22 of 203Chinese Human pairwise preferences in the stated text vote pool Arena 1,526 #20 of 198overall · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,457 #32 of 198overall Human pairwise preferences in the stated text vote pool Arena 1,485 #16 of 196overall · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,457 #32 of 188Spanish Human pairwise preferences in the stated text vote pool Arena 1,442 #54 of 168German Human pairwise preferences in the stated text vote pool Arena 1,475 #16 of 167French Human pairwise preferences in the stated text vote pool Arena 1,472 #33 of 164Korean Human pairwise preferences in the stated text vote pool Arena 1,442 #18 of 156Japanese Human pairwise preferences in the stated text vote pool Arena 1,473 #14 of 152Polish Human pairwise preferences in the stated text vote pool Arena 1,458 #24 of 142
AA Omniscience Index Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA 18.9 #28 of 320
SimpleQA Verifiedv1 Accuracy on short factual questions with verified answers, answered without web access 69.7% #9 of 84
AA OmniscienceAccuracy Measures correct answers on the AA Omniscience factual knowledge test AA 57.2% #8 of 320+1 versions & slices Hallucination Rate Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test AA 89.4% #243 of 320
IFBench (instructions) Checks whether the model follows precise formatting and content instructions AA 66.5% #66 of 245
Mystery Game Puzzles Models choose the best move in puzzle positions from an undisclosed game Epoch 26% #28 of 65
Reasoning 6
ARC-AGI-2semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 42.5% #36 of 69+1 versions & slices public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 38.5% #35 of 66
Chess Puzzles Models choose the best next move from a novel chess position Epoch 31% #42 of 69
ARC-AGI-1semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 74.5% #40 of 67+1 versions & slices public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 84.5% #37 of 64
ARC-AGI-3semi-private Measures interactive game solving through relative human action efficiency ARC 0.3% #15 of 19
Math 5
FrontierMath Tiers 1–3 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 89.1% #6 of 70
FrontierMath Tier 4 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 82.9% #7 of 55
MathArenaArXivMath · June 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 88.5% #5 of 24+1 versions & slices BrokenArXiv · June 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 67.3% #8 of 24
FrontierMath Erdos Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 0% #6 of 13
Science 3
Humanity's Last Exam Very hard expert questions across many fields, written to stump today’s models AA 39.4% #50 of 336
CritPt (physics) Research-level physics problems that need many careful reasoning steps AA 14.9% #47 of 323
Vals Science Index Scientific problem solving across the index’s component evaluations Vals 41.5% #8 of 19
Health & law 5
MLCR-AA Models synthesize long medical records; the headline credits concise answers judged both accurate and complete AA 23.3% #14 of 103
Vals LegalBench Legal reasoning and legal-language understanding on LegalBench Vals 87% #6 of 89
Vals MedScribe Accuracy of clinical notes produced from consultation transcripts Vals 85.2% #28 of 80
Vals MedCode Medical coding accuracy on patient encounters Vals 44% #35 of 78
Vals Legal Research Bench Grounded legal research; a task passes only if all criteria pass Vals 48.1% #8 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 78% #69 of 314
GDP.pdfAA all-pass Models reason over professional PDF documents; an attempt passes only when every atomic criterion passes 21% #23 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 89.8% #35 of 312+1 versions & slices Epoch Models answer graduate-level science multiple-choice questions Epoch 89.9% #34 of 134
OTIS Mock AIME 20242025 Models solve the stated OTIS mock AIME mathematics problems Epoch 95.6% #32 of 131
No benchmark matches