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 20.6 #119 of 336
Knowledge 18
Arena TextEnglish Human pairwise preferences in the stated text vote pool Arena 1,379 #120 of 205+13 versions & slices instruction following Human pairwise preferences in the stated text vote pool Arena 1,357 #112 of 205non-English Human pairwise preferences in the stated text vote pool Arena 1,363 #111 of 205Russian Human pairwise preferences in the stated text vote pool Arena 1,362 #113 of 203Chinese Human pairwise preferences in the stated text vote pool Arena 1,385 #121 of 198overall · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,373 #108 of 198overall Human pairwise preferences in the stated text vote pool Arena 1,390 #106 of 196overall · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,373 #104 of 188Spanish Human pairwise preferences in the stated text vote pool Arena 1,355 #118 of 168German Human pairwise preferences in the stated text vote pool Arena 1,366 #96 of 167French Human pairwise preferences in the stated text vote pool Arena 1,386 #105 of 164Korean Human pairwise preferences in the stated text vote pool Arena 1,306 #101 of 156Japanese Human pairwise preferences in the stated text vote pool Arena 1,341 #82 of 152Polish Human pairwise preferences in the stated text vote pool Arena 1,378 #88 of 142
AA Omniscience Index Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA -11 #102 of 320
AA OmniscienceAccuracy Measures correct answers on the AA Omniscience factual knowledge test AA 23.1% #130 of 320+1 versions & slices Hallucination Rate Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test AA 44.3% #74 of 320
IFBench (instructions) Checks whether the model follows precise formatting and content instructions AA 71.2% #45 of 245
Reasoning 4
ARC-AGI-2semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 4.4% #56 of 69+1 versions & slices public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 5.8% #47 of 66
ARC-AGI-1semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 54.3% #51 of 67+1 versions & slices public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 61.5% #50 of 64
Math 14
MathArenaApex Answer accuracy on the named mathematics competition under the recorded effort MathArena 1% #25 of 34+13 versions & slices AIME 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 87.5% #16 of 30Apex Shortlist Answer accuracy on the named mathematics competition under the recorded effort MathArena 39.9% #26 of 30HMMT February 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 89.2% #9 of 30BRUMO 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 90% #14 of 24SMT 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 89.2% #8 of 24CMIMC 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 84.4% #10 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 85% #16 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 70.8% #9 of 17Kangaroo 2025 7-8 Answer accuracy on the named mathematics competition under the recorded effort MathArena 87.5% #11 of 16Kangaroo 2025 9-10 Answer accuracy on the named mathematics competition under the recorded effort MathArena 97.5% #8 of 16HMMT November 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 84.2% #10 of 14
Science 2
Humanity's Last Exam Very hard expert questions across many fields, written to stump today’s models AA 15.9% #141 of 336
CritPt (physics) Research-level physics problems that need many careful reasoning steps AA 1.4% #115 of 323
Health & law 4
MLCR-AA Models synthesize long medical records; the headline credits concise answers judged both accurate and complete AA 8.9% #61 of 103
Vals LegalBench Legal reasoning and legal-language understanding on LegalBench Vals 81.8% #58 of 89
Vals MedScribe Accuracy of clinical notes produced from consultation transcripts Vals 80.6% #47 of 80
Vals MedCode Medical coding accuracy on patient encounters Vals 43.1% #40 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 72.3% #108 of 314
GDP.pdfAA all-pass Models reason over professional PDF documents; an attempt passes only when every atomic criterion passes 8.4% #68 of 135
Legacy · saturated or no longer reported 2
GPQA Diamond Graduate-level biology, chemistry and physics questions that can’t be solved by a quick web search 80.3% #114 of 312
AIME2025 · AA archived AA evaluates the 30 integer-answer problems from the 2025 AIME mathematics competition AA 85% #29 of 139
No benchmark matches
OpenKimi K3unstatedwins 55%+773%$3 / $15Sampling parameters are fixed+3
BetterGemini 3 Flash Previewunstatedwins 54%+64%$0.50 / $3
Qwen3.5 397B A17BunstatedOpenwins 53%+96%$0.60 / $3.60Context: 400K → 262K
GLM 4.5VunstatedOpensame+31%$0.60 / $1.80Context: 400K → 66K