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 41.8 #28 of 336
Knowledge 21
Arena TextEnglish Human pairwise preferences in the stated text vote pool Arena 1,469 #29 of 205+13 versions & slices instruction following Human pairwise preferences in the stated text vote pool Arena 1,476 #19 of 205non-English Human pairwise preferences in the stated text vote pool Arena 1,450 #29 of 205Russian Human pairwise preferences in the stated text vote pool Arena 1,474 #20 of 203Chinese Human pairwise preferences in the stated text vote pool Arena 1,506 #34 of 198overall · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,461 #29 of 198overall Human pairwise preferences in the stated text vote pool Arena 1,481 #19 of 196overall · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,461 #29 of 188Spanish Human pairwise preferences in the stated text vote pool Arena 1,465 #25 of 168German Human pairwise preferences in the stated text vote pool Arena 1,473 #18 of 167French Human pairwise preferences in the stated text vote pool Arena 1,481 #25 of 164Korean Human pairwise preferences in the stated text vote pool Arena 1,430 #23 of 156Japanese Human pairwise preferences in the stated text vote pool Arena 1,442 #25 of 152Polish Human pairwise preferences in the stated text vote pool Arena 1,459 #23 of 142
AA Omniscience Index Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA 28.8 #15 of 320
SimpleQA Verifiedv1 Accuracy on short factual questions with verified answers, answered without web access 53% #21 of 84
AA OmniscienceAccuracy Measures correct answers on the AA Omniscience factual knowledge test AA 48.8% #28 of 320+1 versions & slices Hallucination Rate Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test AA 39.3% #59 of 320
IFBench (instructions) Checks whether the model follows precise formatting and content instructions AA 62.2% #80 of 245
Mystery Game Puzzles Models choose the best move in puzzle positions from an undisclosed game Epoch 36% #17 of 65
EQ-Bench3 Judge-rated responses to social and emotionally nuanced scenarios, scored through the source pairwise ranking EQ-Bench 2,058 #2 of 53
Reasoning 4
ARC-AGI-2semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 72.1% #21 of 69
Chess Puzzles Models choose the best next move from a novel chess position Epoch 52% #13 of 69
ARC-AGI-1semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 92.5% #22 of 67
ARC-AGI-3semi-private Measures interactive game solving through relative human action efficiency ARC 1.5% #11 of 19
Math 25 Leads on 2
FrontierMath Tiers 1–3 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 80% #17 of 70
FrontierMath Tier 4 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 56.1% #17 of 55
FrontierMath Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 47.2% #3 of 40
MathArenaApex Answer accuracy on the named mathematics competition under the recorded effort MathArena 81.3% #1 of 34+20 versions & slices Apex Shortlist Answer accuracy on the named mathematics competition under the recorded effort MathArena 90.4% #4 of 30AIME 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 100% #1 of 24HMMT February 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 95.5% #6 of 24ArXivMath · June 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 70% #13 of 24BrokenArXiv · June 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 41.7% #15 of 24ArXivMath · February 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 60.2% #4 of 20ArXivMath · May 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 65% #9 of 19BrokenArXiv · May 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 23% #11 of 18ArXivMath · April 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 62.5% #8 of 17Kangaroo 2025 1-2 Answer accuracy on the named mathematics competition under the recorded effort MathArena 70.8% #10 of 17Kangaroo 2025 11-12 Answer accuracy on the named mathematics competition under the recorded effort MathArena 100% #1 of 17Kangaroo 2025 3-4 Answer accuracy on the named mathematics competition under the recorded effort MathArena 60.4% #14 of 17Kangaroo 2025 5-6 Answer accuracy on the named mathematics competition under the recorded effort MathArena 70% #10 of 17Kangaroo 2025 7-8 Answer accuracy on the named mathematics competition under the recorded effort MathArena 96.7% #1 of 16Kangaroo 2025 9-10 Answer accuracy on the named mathematics competition under the recorded effort MathArena 91.7% #13 of 16BrokenArXiv · April 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 34.4% #6 of 15BrokenArXiv · February 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 35.5% #3 of 15ArXivMath · March 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 75% #2 of 14BrokenArXiv · March 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 35.7% #3 of 13ArXivLean · June 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 23.9% #4 of 9
FrontierMath Tier4 Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 31.3% #1 of 33
Science 2
Humanity's Last Exam Very hard expert questions across many fields, written to stump today’s models AA 48.7% #14 of 336
CritPt (physics) Research-level physics problems that need many careful reasoning steps AA 20.9% #27 of 323
Health & law 5
MLCR-AA Models synthesize long medical records; the headline credits concise answers judged both accurate and complete AA 19.4% #26 of 103
Vals LegalBench Legal reasoning and legal-language understanding on LegalBench Vals 83.6% #44 of 89
Vals MedScribe Accuracy of clinical notes produced from consultation transcripts Vals 85.8% #24 of 80
Vals MedCode Medical coding accuracy on patient encounters Vals 53.2% #8 of 78
Vals Legal Research Bench Grounded legal research; a task passes only if all criteria pass Vals 43.8% #19 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 77.7% #75 of 314
GDP.pdfAA all-pass Models reason over professional PDF documents; an attempt passes only when every atomic criterion passes 22.8% #16 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% #21 of 312+1 versions & slices Epoch Models answer graduate-level science multiple-choice questions Epoch 91% #24 of 134
OTIS Mock AIME 20242025 Models solve the stated OTIS mock AIME mathematics problems Epoch 98.3% #21 of 131
No benchmark matches
CheaperKimi K3unstatedOpensame-40%$3 / $15Sampling parameters are fixed+3
CheaperGPT-5.4unstatedsame-44%$2.50 / $15
CheaperGemini 3.6 Flashunstatedsame-85%*$0.75 / $3.75
GLM 4.5VunstatedOpenwins 47%-91%$0.60 / $1.80Context: 1M → 66K