Benchmark By Score Rank
Overall 1
AA Intelligence Index4.3.2 AA Intelligence Index 4.3.2: Artificial Analysis combines tests of knowledge, reasoning, coding and tool use into one score AA 23 #94 of 334
Knowledge 17
Arena Text Arena Text · overall: Human pairwise preferences in the stated text vote pool Arena 1,435 #70 of 196+12 versions & slices English Arena Text · english: Human pairwise preferences in the stated text vote pool Arena 1,409 #92 of 188instruction following Arena Text · instruction following: Human pairwise preferences in the stated text vote pool Arena 1,388 #88 of 188non-English Arena Text · non english: Human pairwise preferences in the stated text vote pool Arena 1,397 #84 of 188overall · full cohort Arena Text · overall · snapshot 2026-10-15 · native board settings: Human pairwise preferences in the stated text vote pool Arena 1,406 #87 of 188Russian Arena Text · russian: Human pairwise preferences in the stated text vote pool Arena 1,402 #79 of 186Chinese Arena Text · chinese: Human pairwise preferences in the stated text vote pool Arena 1,422 #95 of 181Spanish Arena Text · spanish: Human pairwise preferences in the stated text vote pool Arena 1,388 #94 of 155German Arena Text · german: Human pairwise preferences in the stated text vote pool Arena 1,416 #63 of 154French Arena Text · french: Human pairwise preferences in the stated text vote pool Arena 1,408 #87 of 149Korean Arena Text · korean: Human pairwise preferences in the stated text vote pool Arena 1,357 #74 of 144Japanese Arena Text · japanese: Human pairwise preferences in the stated text vote pool Arena 1,402 #43 of 138Polish Arena Text · polish: Human pairwise preferences in the stated text vote pool Arena 1,412 #62 of 133
AA Omniscience Index AA Omniscience Index: Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA -8.7 #89 of 318
AA OmniscienceAccuracy AA Omniscience · Accuracy: Measures correct answers on the AA Omniscience factual knowledge test AA 40.3% #46 of 318+1 versions & slices Hallucination Rate AA Omniscience · Hallucination Rate: Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test AA 82.2% #180 of 318
IFBench (instructions) IFBench (instructions): Checks whether the model follows precise formatting and content instructions AA 73.1% #33 of 245
Reasoning 4
ARC-AGI-2semi-private ARC-AGI-2 · semi-private: Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 9.9% #46 of 66+1 versions & slices public evaluation ARC-AGI-2 · public-eval: Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 9.6% #42 of 63
ARC-AGI-1semi-private ARC-AGI-1 · semi-private: Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 65.7% #41 of 64+1 versions & slices public evaluation ARC-AGI-1 · public-eval: Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 65.9% #43 of 61
Math 15
MathArenaApex MathArena · apex · Apex: Answer accuracy on the named mathematics competition under the recorded effort MathArena 1% #25 of 34+14 versions & slices AIME 2025 MathArena · aime · AIME 2025: Answer accuracy on the named mathematics competition under the recorded effort MathArena 95% #6 of 30HMMT February 2025 MathArena · hmmt · HMMT Feb 2025: Answer accuracy on the named mathematics competition under the recorded effort MathArena 88.3% #10 of 30BRUMO 2025 MathArena · brumo · BRUMO 2025: Answer accuracy on the named mathematics competition under the recorded effort MathArena 91.7% #12 of 24SMT 2025 MathArena · smt · SMT 2025: Answer accuracy on the named mathematics competition under the recorded effort MathArena 92% #3 of 24CMIMC 2025 MathArena · cmimc · CMIMC 2025: Answer accuracy on the named mathematics competition under the recorded effort MathArena 88.8% #8 of 22Kangaroo 2025 1-2 MathArena · kangaroo · Kangaroo 2025 1-2: Answer accuracy on the named mathematics competition under the recorded effort MathArena 68.8% #11 of 17Kangaroo 2025 11-12 MathArena · kangaroo · Kangaroo 2025 11-12: Answer accuracy on the named mathematics competition under the recorded effort MathArena 95% #9 of 17Kangaroo 2025 3-4 MathArena · kangaroo · Kangaroo 2025 3-4: Answer accuracy on the named mathematics competition under the recorded effort MathArena 60.4% #14 of 17Kangaroo 2025 5-6 MathArena · kangaroo · Kangaroo 2025 5-6: Answer accuracy on the named mathematics competition under the recorded effort MathArena 65% #14 of 17Kangaroo 2025 7-8 MathArena · kangaroo · Kangaroo 2025 7-8: Answer accuracy on the named mathematics competition under the recorded effort MathArena 90.8% #5 of 16Kangaroo 2025 9-10 MathArena · kangaroo · Kangaroo 2025 9-10: Answer accuracy on the named mathematics competition under the recorded effort MathArena 92.5% #12 of 16HMMT November 2025 MathArena · hmmt · HMMT Nov 2025: Answer accuracy on the named mathematics competition under the recorded effort MathArena 89.2% #7 of 14Project Euler MathArena · euler · Project Euler: Answer accuracy on the named mathematics competition under the recorded effort MathArena 56.7% #9 of 11IMO 2025 MathArena · imo · IMO 2025: Answer accuracy on the named mathematics competition under the recorded effort MathArena 38.1% #1 of 4
Science 2
Humanity's Last Exam Humanity's Last Exam: Very hard expert questions across many fields, written to stump today’s models AA 28.5% #88 of 334
CritPt (physics) CritPt (physics): Research-level physics problems that need many careful reasoning steps AA 5.7% #75 of 321
Health & law 3
Vals LegalBench Vals LegalBench: Legal reasoning and legal-language understanding on LegalBench Vals 86% #14 of 89
Vals MedScribe Vals MedScribe: Accuracy of clinical notes produced from consultation transcripts Vals 83.7% #38 of 80
Vals MedCode Vals MedCode: Medical coding accuracy on patient encounters Vals 49.6% #17 of 78
Documents 1
AA-LCR (long context)1.1 AA-LCR (long context) 1.1: Questions that need reading and connecting facts across very long documents (around 100K tokens) AA 78.2% #67 of 273
Legacy · saturated or no longer reported 2
GPQA Diamond GPQA Diamond: Graduate-level biology, chemistry and physics questions that can’t be solved by a quick web search 85.4% #79 of 312
AIME2025 · AA archived AIME 2025 · AA archived: AA evaluates the 30 integer-answer problems from the 2025 AIME mathematics competition AA 94.3% #7 of 139
No benchmark matches
CheaperGemini 3.8 Flashhigh×9.7-56%*$1.24Sampling parameters are ignored+1
OpenGLM 5.3 Flashmax×7-93%$0.28Defaults to max · Self-hosted+4
CheaperGrok 4.6high×7.1-13%$1.48
Claude Haiku 5.5xhigh×6.7-94%$0.12Remove sampling parameters+5
DeepSeek V4 Pro 0813highOpen×6.6-42%$1.32 / $3.96No image input+5
Kimi K3maxOpen×6.4+75%$2.00Sampling parameters are fixed+3TInkling SmallxhighOpen×4.1-81%$0.45 / $1.20Context: 400K → 256K+1
Qwen3.8 27BxhighOpen×4-72%$1.01Context: 400K → 262K+5