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 19.3 #122 of 334
Knowledge 19
Arena Text Human pairwise preferences in the stated text vote pool Arena 1,456 #43 of 196+12 versions & slices English Human pairwise preferences in the stated text vote pool Arena 1,450 #49 of 188instruction following Human pairwise preferences in the stated text vote pool Arena 1,459 #30 of 188non-English Human pairwise preferences in the stated text vote pool Arena 1,425 #55 of 188overall · full cohort Human pairwise preferences in the stated text vote pool Arena 1,438 #52 of 188Russian Human pairwise preferences in the stated text vote pool Arena 1,436 #45 of 186Chinese Human pairwise preferences in the stated text vote pool Arena 1,460 #73 of 181Spanish Human pairwise preferences in the stated text vote pool Arena 1,458 #30 of 155German Human pairwise preferences in the stated text vote pool Arena 1,421 #56 of 154French Human pairwise preferences in the stated text vote pool Arena 1,458 #43 of 149Korean Human pairwise preferences in the stated text vote pool Arena 1,402 #40 of 144Japanese Human pairwise preferences in the stated text vote pool Arena 1,390 #54 of 138Polish Human pairwise preferences in the stated text vote pool Arena 1,419 #58 of 133
AA Omniscience Index Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA -9.4 #90 of 318
SimpleQA Verifiedv1 Accuracy on short factual questions with verified answers, answered without web access 29.2% #59 of 83
AA OmniscienceAccuracy Measures correct answers on the AA Omniscience factual knowledge test AA 28.4% #86 of 318+1 versions & slices Hallucination Rate Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test AA 52.7% #95 of 318
IFBench (instructions) Checks whether the model follows precise formatting and content instructions AA 42.7% #142 of 245
EQ-Bench3 Judge-rated responses to social and emotionally nuanced scenarios, scored through the source pairwise ranking EQ-Bench 1,511 #20 of 50
Reasoning 5
Chess Puzzles Models choose the best next move from a novel chess position Epoch 6% #63 of 68
ARC-AGI-2semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 13.6% #43 of 66+1 versions & slices public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 14.7% #39 of 63
ARC-AGI-1semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 63.7% #43 of 64+1 versions & slices public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 73.8% #40 of 61
Math 14
FrontierMath Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 9.3% #26 of 40
MathArenaApex Answer accuracy on the named mathematics competition under the recorded effort MathArena 1.6% #23 of 34+11 versions & slices AIME 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 84.2% #19 of 30HMMT February 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 67.5% #21 of 30BRUMO 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 90.8% #13 of 24SMT 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 84% #15 of 24CMIMC 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 66.3% #19 of 22Kangaroo 2025 1-2 Answer accuracy on the named mathematics competition under the recorded effort MathArena 61.5% #15 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 62.5% #13 of 17Kangaroo 2025 5-6 Answer accuracy on the named mathematics competition under the recorded effort MathArena 68.3% #11 of 17Kangaroo 2025 7-8 Answer accuracy on the named mathematics competition under the recorded effort MathArena 80% #15 of 16Kangaroo 2025 9-10 Answer accuracy on the named mathematics competition under the recorded effort MathArena 95% #11 of 16
FrontierMath Tier4 Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 2.1% #23 of 33
Science 2
Humanity's Last Exam Very hard expert questions across many fields, written to stump today’s models AA 7.2% #220 of 334
CritPt (physics) Research-level physics problems that need many careful reasoning steps AA 0% #178 of 321
Health & law 3
Vals LegalBench Legal reasoning and legal-language understanding on LegalBench Vals 84.1% #34 of 89
Vals MedScribe Accuracy of clinical notes produced from consultation transcripts Vals 84.1% #34 of 80
Vals MedCode Medical coding accuracy on patient encounters Vals 44.1% #34 of 78
Documents 2
AA-LCR (long context)1.1 Questions that need reading and connecting facts across very long documents (around 100K tokens) AA 54% #168 of 273
GDP.pdfAA all-pass Models reason over professional PDF documents; an attempt passes only when every atomic criterion passes 5.2% #85 of 133
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 72.7% #168 of 312+1 versions & slices Epoch Models answer graduate-level science multiple-choice questions Epoch 73.7% #76 of 133
AIME2025 · AA archived AA evaluates the 30 integer-answer problems from the 2025 AIME mathematics competition AA 37% #98 of 139
OTIS Mock AIME 20242025 Models solve the stated OTIS mock AIME mathematics problems Epoch 35.6% #100 of 130
No benchmark matches
CheaperGemini 3 Flash Previewunstatedsame-81%$0.50 / $3
OpenGLM 5unstatedsame-74%$1 / $3.20Context: 1M → 203K+1
CheaperKimi K2.5unstatedOpensame-80%$0.60 / $3Context: 1M → 256K
CheaperGPT-5.2highsame-20%$1.75 / $14Context: 1M → 400K
DeepSeek V3.2 SpecialeunstatedOpensame——Context: 1M → 128K+1