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 26.3 #76 of 336
Knowledge 31
Arena TextEnglish Human pairwise preferences in the stated text vote pool Arena 1,441 #65 of 205+24 versions & slices instruction following Human pairwise preferences in the stated text vote pool Arena 1,414 #71 of 205non-English Human pairwise preferences in the stated text vote pool Arena 1,438 #37 of 205Russian Human pairwise preferences in the stated text vote pool Arena 1,454 #33 of 203Chinese Human pairwise preferences in the stated text vote pool Arena 1,477 #59 of 198overall · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,442 #47 of 198overall Human pairwise preferences in the stated text vote pool Arena 1,458 #41 of 196overall · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,442 #46 of 188Spanish Human pairwise preferences in the stated text vote pool Arena 1,427 #69 of 168German Human pairwise preferences in the stated text vote pool Arena 1,465 #24 of 167French Human pairwise preferences in the stated text vote pool Arena 1,445 #67 of 164Korean Human pairwise preferences in the stated text vote pool Arena 1,417 #32 of 156Japanese Human pairwise preferences in the stated text vote pool Arena 1,425 #32 of 152Polish Human pairwise preferences in the stated text vote pool Arena 1,469 #15 of 142Chinese · minimal effort Human pairwise preferences in the stated text vote pool Arena 1,477 #1 of 1English · minimal effort Human pairwise preferences in the stated text vote pool Arena 1,441 #1 of 1French · minimal effort Human pairwise preferences in the stated text vote pool Arena 1,445 #1 of 1German · minimal effort Human pairwise preferences in the stated text vote pool Arena 1,466 #1 of 1instruction following · minimal effort Human pairwise preferences in the stated text vote pool Arena 1,414 #1 of 1Japanese · minimal effort Human pairwise preferences in the stated text vote pool Arena 1,425 #1 of 1Korean · minimal effort Human pairwise preferences in the stated text vote pool Arena 1,418 #1 of 1non-English · minimal effort Human pairwise preferences in the stated text vote pool Arena 1,438 #1 of 1Polish · minimal effort Human pairwise preferences in the stated text vote pool Arena 1,468 #1 of 1Russian · minimal effort Human pairwise preferences in the stated text vote pool Arena 1,454 #1 of 1Spanish · minimal effort Human pairwise preferences in the stated text vote pool Arena 1,427 #1 of 1
AA Omniscience Index Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA 10.1 #43 of 320
SimpleQA Verifiedv1 Accuracy on short factual questions with verified answers, answered without web access 66.8% #10 of 84
AA OmniscienceAccuracy Measures correct answers on the AA Omniscience factual knowledge test AA 53.4% #14 of 320+1 versions & slices Hallucination Rate Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test AA 92.4% #278 of 320
IFBench (instructions) Checks whether the model follows precise formatting and content instructions AA 78% #9 of 245
Mystery Game Puzzles Models choose the best move in puzzle positions from an undisclosed game Epoch 25% #30 of 65
Reasoning 5
ARC-AGI-2semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 3.3% #57 of 69+1 versions & slices public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 2.1% #54 of 66
Chess Puzzles Models choose the best next move from a novel chess position Epoch 39% #31 of 69
ARC-AGI-1semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 21.5% #57 of 67+1 versions & slices public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 31.9% #55 of 64
Math 23
FrontierMath Tiers 1–3 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 51.2% #46 of 70
FrontierMath Tier 4 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 17.1% #43 of 55
FrontierMath Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 35.6% #10 of 40
MathArenaApex Answer accuracy on the named mathematics competition under the recorded effort MathArena 15.6% #14 of 34+18 versions & slices AIME 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 97.5% #2 of 30Apex Shortlist Answer accuracy on the named mathematics competition under the recorded effort MathArena 68.6% #15 of 30HMMT February 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 97.5% #2 of 30AIME 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 96.7% #6 of 24HMMT February 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 89.4% #13 of 24BRUMO 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 100% #1 of 24SMT 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 92.9% #2 of 24CMIMC 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 90% #7 of 22ArXivMath · January 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 58.2% #10 of 18Kangaroo 2025 1-2 Answer accuracy on the named mathematics competition under the recorded effort MathArena 87.5% #4 of 17Kangaroo 2025 11-12 Answer accuracy on the named mathematics competition under the recorded effort MathArena 95.8% #7 of 17Kangaroo 2025 3-4 Answer accuracy on the named mathematics competition under the recorded effort MathArena 66.7% #8 of 17Kangaroo 2025 5-6 Answer accuracy on the named mathematics competition under the recorded effort MathArena 77.5% #7 of 17Kangaroo 2025 7-8 Answer accuracy on the named mathematics competition under the recorded effort MathArena 89.2% #8 of 16Kangaroo 2025 9-10 Answer accuracy on the named mathematics competition under the recorded effort MathArena 98.3% #7 of 16HMMT November 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 93.3% #3 of 14ArXivMath · December 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 43.4% #5 of 13Project Euler Answer accuracy on the named mathematics competition under the recorded effort MathArena 61.8% #6 of 11
FrontierMath Tier4 Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 4.2% #16 of 33
Science 2
Humanity's Last Exam Very hard expert questions across many fields, written to stump today’s models AA 36.6% #60 of 336
CritPt (physics) Research-level physics problems that need many careful reasoning steps AA 8.6% #68 of 323
Health & law 5
MLCR-AA Models synthesize long medical records; the headline credits concise answers judged both accurate and complete AA 11.7% #49 of 103
Vals LegalBench Legal reasoning and legal-language understanding on LegalBench Vals 86.9% #8 of 89
Vals MedScribe Accuracy of clinical notes produced from consultation transcripts Vals 69.9% #70 of 80
Vals MedCode Medical coding accuracy on patient encounters Vals 55.9% #5 of 78
Vals Legal Research Bench Grounded legal research; a task passes only if all criteria pass Vals 18.3% #53 of 73
Documents 1
AA-LCR (long context)1.1 Questions that need reading and connecting facts across very long documents (around 100K tokens) AA 78% #70 of 314
Legacy · saturated or no longer reported 4
GPQA Diamond Graduate-level biology, chemistry and physics questions that can’t be solved by a quick web search 89.8% #36 of 312+1 versions & slices Epoch Models answer graduate-level science multiple-choice questions Epoch 89.4% #38 of 134
AIME2025 · AA archived AA evaluates the 30 integer-answer problems from the 2025 AIME mathematics competition AA 97% #2 of 139
OTIS Mock AIME 20242025 Models solve the stated OTIS mock AIME mathematics problems Epoch 95.6% #33 of 131
No benchmark matches
CheaperDeepSeek V4.1 Flash 1017maxOpen+96%-53%$0.26No PDF input+5
BetterClaude Haiku 5.5max+20%-82%$0.21Remove sampling parameters+5
CheaperQwen3.6 35B A3BnoneOpen-12%-50%$0.25 / $1.49Context: 1M → 262K+1
CheaperGPT-5.6 Lunamax-16%-60%$0.18
GLM 5.3maxOpen+32%+91%$2.01No image input+5
Kimi K3maxOpen+4%+433%$2.00Sampling parameters are fixed+3