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 29.7 #60 of 336
Knowledge 22
Arena TextEnglish Human pairwise preferences in the stated text vote pool Arena 1,478 #18 of 205+13 versions & slices instruction following Human pairwise preferences in the stated text vote pool Arena 1,466 #25 of 205non-English Human pairwise preferences in the stated text vote pool Arena 1,476 #11 of 205Russian Human pairwise preferences in the stated text vote pool Arena 1,497 #8 of 203Chinese Human pairwise preferences in the stated text vote pool Arena 1,529 #17 of 198overall · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,480 #13 of 198overall Human pairwise preferences in the stated text vote pool Arena 1,487 #14 of 196overall · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,480 #13 of 188Spanish Human pairwise preferences in the stated text vote pool Arena 1,480 #10 of 168German Human pairwise preferences in the stated text vote pool Arena 1,490 #10 of 167French Human pairwise preferences in the stated text vote pool Arena 1,488 #20 of 164Korean Human pairwise preferences in the stated text vote pool Arena 1,455 #14 of 156Japanese Human pairwise preferences in the stated text vote pool Arena 1,493 #8 of 152Polish Human pairwise preferences in the stated text vote pool Arena 1,497 #6 of 142
AA Omniscience Index Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA 31.9 #10 of 320
SimpleQA Verifiedv1 Accuracy on short factual questions with verified answers, answered without web access 73.5% #5 of 84
AA OmniscienceAccuracy Measures correct answers on the AA Omniscience factual knowledge test AA 54.9% #10 of 320+1 versions & slices Hallucination Rate Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test AA 50.9% #92 of 320
IFBench (instructions) Checks whether the model follows precise formatting and content instructions AA 77.1% #12 of 245
Mystery Game Puzzles Models choose the best move in puzzle positions from an undisclosed game Epoch 34% #20 of 65+1 versions & slices August 2026 run Models choose the best move in puzzle positions from an undisclosed game Epoch 29% #1 of 1
EQ-Bench3 Judge-rated responses to social and emotionally nuanced scenarios, scored through the source pairwise ranking EQ-Bench 1,527 #17 of 53
Reasoning 6
ARC-AGI-2semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 77.1% #18 of 69+1 versions & slices public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 88.1% #16 of 66
Chess Puzzles Models choose the best next move from a novel chess position Epoch 51% #14 of 69
ARC-AGI-1semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 98% #7 of 67+1 versions & slices public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 97.2% #18 of 64
ARC-AGI-3semi-private Measures interactive game solving through relative human action efficiency ARC 0.4% #15 of 19
Math 30
FrontierMath Tiers 1–3 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 59.6% #35 of 70
FrontierMath Tier 4 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 26.8% #33 of 55
FrontierMath Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 36.9% #9 of 40
MathArenaApex Answer accuracy on the named mathematics competition under the recorded effort MathArena 60.9% #5 of 34+25 versions & slices Apex Shortlist Answer accuracy on the named mathematics competition under the recorded effort MathArena 92% #2 of 30AIME 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 98.3% #4 of 24HMMT February 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 94.7% #7 of 24ArXivMath · June 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 66.7% #16 of 24BrokenArXiv · June 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 17.6% #19 of 24ArXivMath · February 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 62.5% #3 of 20ArXivMath · May 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 51.7% #17 of 19ArXivMath · January 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 70.7% #6 of 18BrokenArXiv · May 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 17% #14 of 18ArXivMath · April 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 63.8% #7 of 17Kangaroo 2025 1-2 Answer accuracy on the named mathematics competition under the recorded effort MathArena 86.5% #5 of 17Kangaroo 2025 11-12 Answer accuracy on the named mathematics competition under the recorded effort MathArena 97.5% #5 of 17Kangaroo 2025 3-4 Answer accuracy on the named mathematics competition under the recorded effort MathArena 76% #4 of 17Kangaroo 2025 5-6 Answer accuracy on the named mathematics competition under the recorded effort MathArena 86.7% #3 of 17Kangaroo 2025 7-8 Answer accuracy on the named mathematics competition under the recorded effort MathArena 90% #6 of 16Kangaroo 2025 9-10 Answer accuracy on the named mathematics competition under the recorded effort MathArena 100% #1 of 16BrokenArXiv · April 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 25.8% #8 of 15BrokenArXiv · February 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 18.6% #5 of 15ArXivMath · March 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 68.3% #3 of 14ArXivMath · December 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 66.2% #1 of 13BrokenArXiv · March 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 13.8% #7 of 13Project Euler Answer accuracy on the named mathematics competition under the recorded effort MathArena 89% #1 of 11ArXivLean · June 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 10.9% #7 of 9USAMO 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 74.4% #3 of 8ArXivLean · March 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 14.6% #3 of 5
FrontierMath Tier4 Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 16.7% #6 of 33
Science 3
Humanity's Last Exam Very hard expert questions across many fields, written to stump today’s models AA 47% #18 of 336
CritPt (physics) Research-level physics problems that need many careful reasoning steps AA 17.7% #39 of 323
Vals Science Index Scientific problem solving across the index’s component evaluations Vals 27.4% #17 of 19
Health & law 5
MLCR-AA Models synthesize long medical records; the headline credits concise answers judged both accurate and complete AA 11.1% #52 of 103
Vals LegalBench Legal reasoning and legal-language understanding on LegalBench Vals 87.4% #4 of 89
Vals MedScribe Accuracy of clinical notes produced from consultation transcripts Vals 76.1% #59 of 80
Vals MedCode Medical coding accuracy on patient encounters Vals 59.1% #2 of 78
Vals Legal Research Bench Grounded legal research; a task passes only if all criteria pass Vals 20.7% #52 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 82% #29 of 314
GDP.pdfAA all-pass Models reason over professional PDF documents; an attempt passes only when every atomic criterion passes 17.8% #31 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 94.1% #4 of 312+1 versions & slices Epoch Models answer graduate-level science multiple-choice questions Epoch 94.4% #7 of 134
OTIS Mock AIME 20242025 Models solve the stated OTIS mock AIME mathematics problems Epoch 95.6% #32 of 131
No benchmark matches
CheaperQwen3.8 Max (0902)xhigh+5%-33%$2 / $6Context: 1M → 984K
BetterGPT-6 Lunamax+3%-96%$0.068Function calling only with none · Chat Completions+3
OpenDeepSeek V4.1 Flash 1017max+4%-88%$0.26No PDF input+5
CheaperClaude Sonnet 5.5max+5%-11%$5.46No forced tool use+5
Kimi K3maxOpen+2%+33%$2.00Sampling parameters are fixed+3