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 47.6 #12 of 334
Knowledge 18
Arena Text Human pairwise preferences in the stated text vote pool Arena 1,459 #41 of 196+12 versions & slices English Human pairwise preferences in the stated text vote pool Arena 1,397 #97 of 188instruction following Human pairwise preferences in the stated text vote pool Arena 1,413 #69 of 188non-English Human pairwise preferences in the stated text vote pool Arena 1,387 #87 of 188overall · full cohort Human pairwise preferences in the stated text vote pool Arena 1,398 #91 of 188Russian Human pairwise preferences in the stated text vote pool Arena 1,407 #75 of 186Chinese Human pairwise preferences in the stated text vote pool Arena 1,408 #103 of 181Spanish Human pairwise preferences in the stated text vote pool Arena 1,387 #95 of 155German Human pairwise preferences in the stated text vote pool Arena 1,377 #81 of 154French Human pairwise preferences in the stated text vote pool Arena 1,398 #90 of 149Korean Human pairwise preferences in the stated text vote pool Arena 1,337 #83 of 144Japanese Human pairwise preferences in the stated text vote pool Arena 1,372 #63 of 138Polish Human pairwise preferences in the stated text vote pool Arena 1,367 #85 of 133
AA Omniscience Index Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA 27.1 #18 of 318
SimpleQA Verifiedv1 Accuracy on short factual questions with verified answers, answered without web access 60.7% #14 of 83
AA OmniscienceAccuracy Measures correct answers on the AA Omniscience factual knowledge test AA 54.5% #12 of 318+1 versions & slices Hallucination Rate Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test AA 60.1% #105 of 318
Mystery Game Puzzles Models choose the best move in puzzle positions from an undisclosed game Epoch 56% #9 of 64
Reasoning 6
Chess Puzzles Models choose the best next move from a novel chess position Epoch 56% #11 of 68
ARC-AGI-2semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 89.6% #8 of 66+1 versions & slices public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 90% #14 of 63
ARC-AGI-1semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 95.5% #14 of 64+1 versions & slices public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 97.8% #13 of 61
ARC-AGI-3semi-private Measures interactive game solving through relative human action efficiency ARC 4.6% #7 of 18
Math 9
FrontierMath Tiers 1–3 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 89.8% #5 of 69
FrontierMath Tier 4 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 90% #5 of 54
MathArenaArXivMath · June 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 91% #3 of 24+5 versions & slices BrokenArXiv · June 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 95.4% #4 of 24ArXivMath · May 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 90% #3 of 19BrokenArXiv · May 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 87% #4 of 18ArXivMath · August 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 93% #2 of 12BrokenArXiv · August 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 78.6% #4 of 12
FrontierMath Erdos Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 1.5% #5 of 13
Science 3
Humanity's Last Exam Very hard expert questions across many fields, written to stump today’s models AA 47.9% #16 of 334
CritPt (physics) Research-level physics problems that need many careful reasoning steps AA 30.9% #8 of 321
Vals Science Index Scientific problem solving across the index’s component evaluations Vals 45% #7 of 18
Health & law 4
Vals MedScribe Accuracy of clinical notes produced from consultation transcripts Vals 82% #44 of 80
Vals MedCode Medical coding accuracy on patient encounters Vals 47.1% #29 of 78
Vals Legal Research Bench Grounded legal research; a task passes only if all criteria pass Vals 28.9% #42 of 69
MLCR-AA Models synthesize long medical records; the headline credits concise answers judged both accurate and complete AA 16.1% #30 of 64
Documents 2
AA-LCR (long context)1.1 Questions that need reading and connecting facts across very long documents (around 100K tokens) AA 83.7% #10 of 273
GDP.pdfAA all-pass Models reason over professional PDF documents; an attempt passes only when every atomic criterion passes 25.2% #10 of 133
Legacy · saturated or no longer reported 2
GPQA DiamondEpoch Models answer graduate-level science multiple-choice questions Epoch 94.3% #8 of 133
OTIS Mock AIME 20242025 Models solve the stated OTIS mock AIME mathematics problems Epoch 100% #1 of 130
No benchmark matches