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 31.9 #54 of 336
Knowledge 21
Arena TextEnglish Human pairwise preferences in the stated text vote pool Arena 1,511 #3 of 205+13 versions & slices instruction following Human pairwise preferences in the stated text vote pool Arena 1,521 #3 of 205non-English Human pairwise preferences in the stated text vote pool Arena 1,488 #7 of 205Russian Human pairwise preferences in the stated text vote pool Arena 1,496 #9 of 203Chinese Human pairwise preferences in the stated text vote pool Arena 1,551 #6 of 198overall · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,501 #5 of 198overall Human pairwise preferences in the stated text vote pool Arena 1,503 #5 of 196overall · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,502 #5 of 188Spanish Human pairwise preferences in the stated text vote pool Arena 1,509 #4 of 168German Human pairwise preferences in the stated text vote pool Arena 1,502 #4 of 167French Human pairwise preferences in the stated text vote pool Arena 1,512 #6 of 164Korean Human pairwise preferences in the stated text vote pool Arena 1,463 #6 of 156Japanese Human pairwise preferences in the stated text vote pool Arena 1,488 #10 of 152Polish Human pairwise preferences in the stated text vote pool Arena 1,497 #4 of 142
AA Omniscience Index Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA 13.7 #35 of 320
SimpleQA Verifiedv1 Accuracy on short factual questions with verified answers, answered without web access 47% #32 of 84
AA OmniscienceAccuracy Measures correct answers on the AA Omniscience factual knowledge test AA 47% #31 of 320+1 versions & slices Hallucination Rate Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test AA 62.8% #114 of 320
IFBench (instructions) Checks whether the model follows precise formatting and content instructions AA 53.1% #107 of 245
Mystery Game Puzzles Models choose the best move in puzzle positions from an undisclosed game Epoch 25% #31 of 65
EQ-Bench3 Judge-rated responses to social and emotionally nuanced scenarios, scored through the source pairwise ranking EQ-Bench 1,712 #4 of 53
Reasoning 5
ARC-AGI-2semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 68.8% #22 of 69+1 versions & slices public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 74.9% #19 of 66
Chess Puzzles Models choose the best next move from a novel chess position Epoch 21% #50 of 69
ARC-AGI-1semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 93% #21 of 67+1 versions & slices public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 96.8% #19 of 64
Math 22
FrontierMath Tiers 1–3 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 66% #29 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 40.7% #5 of 40
MathArenaApex Answer accuracy on the named mathematics competition under the recorded effort MathArena 34.5% #8 of 34+17 versions & slices Apex Shortlist Answer accuracy on the named mathematics competition under the recorded effort MathArena 86.7% #7 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 96.2% #5 of 24ArXivMath · February 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 40.6% #11 of 20ArXivMath · January 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 72.8% #4 of 18Kangaroo 2025 1-2 Answer accuracy on the named mathematics competition under the recorded effort MathArena 59.4% #17 of 17Kangaroo 2025 11-12 Answer accuracy on the named mathematics competition under the recorded effort MathArena 87.5% #14 of 17Kangaroo 2025 3-4 Answer accuracy on the named mathematics competition under the recorded effort MathArena 50% #16 of 17Kangaroo 2025 5-6 Answer accuracy on the named mathematics competition under the recorded effort MathArena 58.3% #17 of 17Kangaroo 2025 7-8 Answer accuracy on the named mathematics competition under the recorded effort MathArena 86.7% #12 of 16Kangaroo 2025 9-10 Answer accuracy on the named mathematics competition under the recorded effort MathArena 91.7% #13 of 16BrokenArXiv · February 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 3.2% #14 of 15ArXivMath · March 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 62.5% #5 of 14ArXivMath · December 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 57.4% #3 of 13BrokenArXiv · March 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 5.8% #12 of 13Project Euler Answer accuracy on the named mathematics competition under the recorded effort MathArena 87.7% #3 of 11USAMO 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 47% #6 of 8
FrontierMath Tier4 Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 22.9% #4 of 33
Science 2
Humanity's Last Exam Very hard expert questions across many fields, written to stump today’s models AA 39.9% #47 of 336
CritPt (physics) Research-level physics problems that need many careful reasoning steps AA 12.6% #52 of 323
Health & law 3
Vals LegalBench Legal reasoning and legal-language understanding on LegalBench Vals 85.3% #18 of 89
Vals MedScribe Accuracy of clinical notes produced from consultation transcripts Vals 86.1% #22 of 80
Vals MedCode Medical coding accuracy on patient encounters Vals 49.1% #22 of 78
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 3
GPQA Diamond Graduate-level biology, chemistry and physics questions that can’t be solved by a quick web search 89.6% #39 of 312+1 versions & slices Epoch Models answer graduate-level science multiple-choice questions Epoch 88.4% #42 of 134
OTIS Mock AIME 20242025 Models solve the stated OTIS mock AIME mathematics problems Epoch 91.1% #44 of 131
No benchmark matches
BetterGPT-6.1 Sollow+4%-60%$0.13Remove unsupported parameters+5
OpenDeepSeek V4.1 Flash 1017high+11%-95%$0.30 / $1.20Pass back reasoning_content · Chat Completions+4
CheaperGemini 4 Argonhigh+30%-60%*$1.62Synchronous output stops at 65,536+2
GLM 5.3 FlashmaxOpen-11%-98%$0.28Defaults to max · Self-hosted+4
Kimi K3maxOpen-18%-40%$2.00Sampling parameters are fixed+3
Muse Spark OpenxhighOpen-24%-80%$0.84Reasoning off leaves output unchanged · Self-hosted / llama.cpp+1