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 13 #167 of 337
Knowledge 4
AA OmniscienceAccuracy Measures correct answers on the AA Omniscience factual knowledge test AA 19.1% #163 of 321+1 versions & slices Hallucination Rate Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test AA 59% #104 of 321
AA Omniscience Index Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA -28.7 #147 of 321
IFBench (instructions) Checks whether the model follows precise formatting and content instructions AA 67.6% #60 of 248
Reasoning 4
ARC-AGI-1public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 29.7% #52 of 61+1 versions & slices semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 20.7% #54 of 64
ARC-AGI-2public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 0.3% #52 of 63+1 versions & slices semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 2.6% #55 of 66
Math 6
MathArenaAIME 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 85% #18 of 30+5 versions & slices BRUMO 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 80.8% #23 of 24CMIMC 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 74.4% #13 of 22HMMT February 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 74.2% #19 of 30HMMT November 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 81.7% #11 of 14SMT 2025 Answer accuracy on the named mathematics competition under the recorded effort MathArena 85.4% #13 of 24
Science 2
Humanity's Last Exam Very hard expert questions across many fields, written to stump today’s models AA 9.5% #200 of 337
CritPt (physics) Research-level physics problems that need many careful reasoning steps AA 0% #180 of 324
Coding 1
Terminal-Bench Hard Agents solve difficult software, system-administration and data-processing tasks in a terminal AA 12.1% #118 of 242
Multimodal 2
MMMU-Pro (vision) College-level questions that require understanding images: charts, diagrams, photos AA 61% #97 of 127
Arena Vision Human pairwise preferences in the stated vision vote pool Arena 1,159 #72 of 88
Writing 14
Arena Textcreative writing Human pairwise preferences in the stated text vote pool Arena 1,246 #161 of 195+13 versions & slices overall Human pairwise preferences in the stated text vote pool Arena 1,338 #135 of 196Chinese Human pairwise preferences in the stated text vote pool Arena 1,356 #126 of 181English Human pairwise preferences in the stated text vote pool Arena 1,322 #139 of 188German Human pairwise preferences in the stated text vote pool Arena 1,327 #106 of 154instruction following Human pairwise preferences in the stated text vote pool Arena 1,306 #129 of 188Japanese Human pairwise preferences in the stated text vote pool Arena 1,226 #102 of 138Korean Human pairwise preferences in the stated text vote pool Arena 1,269 #103 of 144non-English Human pairwise preferences in the stated text vote pool Arena 1,313 #130 of 188Polish Human pairwise preferences in the stated text vote pool Arena 1,314 #104 of 133Russian Human pairwise preferences in the stated text vote pool Arena 1,296 #132 of 186Spanish Human pairwise preferences in the stated text vote pool Arena 1,360 #105 of 155overall · full cohort Human pairwise preferences in the stated text vote pool Arena 1,320 #134 of 188creative writing · full cohort Human pairwise preferences in the stated text vote pool Arena 1,249 #147 of 187
Health & law 3
Vals LegalBench Legal reasoning and legal-language understanding on LegalBench Vals 50.1% #88 of 89
Vals MedCode Medical coding accuracy on patient encounters Vals 30.4% #72 of 78
Vals MedScribe Accuracy of clinical notes produced from consultation transcripts Vals 72.9% #64 of 80
Documents 1
AA-LCR (long context)1.1 Questions that need reading and connecting facts across very long documents (around 100K tokens) AA 45% #187 of 275
Legacy · saturated or no longer reported 4
τ²-benchAA Tests service agents that use tools while coordinating with a simulated user AA 36.5% #134 of 245
AIME2025 · AA archived AA evaluates the 30 integer-answer problems from the 2025 AIME mathematics competition AA 83.7% #34 of 140
LiveCodeBenchAA archived AA evaluates solutions to newly collected competitive-programming problems AA 78.9% #18 of 153
GPQA Diamond Graduate-level biology, chemistry and physics questions that can’t be solved by a quick web search 67.6% #199 of 315
No benchmark matches