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 44.8 #17 of 334
Knowledge 18
Arena Text Arena Text · overall: Human pairwise preferences in the stated text vote pool Arena 1,490 #11 of 196+12 versions & slices English Arena Text · english: Human pairwise preferences in the stated text vote pool Arena 1,507 #5 of 188instruction following Arena Text · instruction following: Human pairwise preferences in the stated text vote pool Arena 1,518 #4 of 188non-English Arena Text · non english: Human pairwise preferences in the stated text vote pool Arena 1,500 #4 of 188overall · full cohort Arena Text · overall · snapshot 2026-10-15 · native board settings: Human pairwise preferences in the stated text vote pool Arena 1,508 #4 of 188Russian Arena Text · russian: Human pairwise preferences in the stated text vote pool Arena 1,507 #6 of 186Chinese Arena Text · chinese: Human pairwise preferences in the stated text vote pool Arena 1,573 #4 of 181Spanish Arena Text · spanish: Human pairwise preferences in the stated text vote pool Arena 1,519 #2 of 155German Arena Text · german: Human pairwise preferences in the stated text vote pool Arena 1,526 #1 of 154French Arena Text · french: Human pairwise preferences in the stated text vote pool Arena 1,520 #2 of 149Korean Arena Text · korean: Human pairwise preferences in the stated text vote pool Arena 1,521 #2 of 144Japanese Arena Text · japanese: Human pairwise preferences in the stated text vote pool Arena 1,515 #2 of 138Polish Arena Text · polish: Human pairwise preferences in the stated text vote pool Arena 1,520 #2 of 133
AA Omniscience Index AA Omniscience Index: Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA 31 #10 of 318
SimpleQA Verifiedv1 SimpleQA Verified v1: Accuracy on short factual questions with verified answers, answered without web access 63.3% #13 of 83
AA OmniscienceAccuracy AA Omniscience · Accuracy: Measures correct answers on the AA Omniscience factual knowledge test AA 57.1% #8 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 60.7% #106 of 318
Mystery Game Puzzles Mystery Game Puzzles: Models choose the best move in puzzle positions from an undisclosed game Epoch 59% #6 of 64
Reasoning 6
Chess Puzzles Chess Puzzles: Models choose the best next move from a novel chess position Epoch 43% #24 of 68
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 90.4% #6 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 97.1% #6 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 97.5% #8 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 99% #2 of 61
ARC-AGI-3semi-private ARC-AGI-3 · semi-private: Measures interactive game solving through relative human action efficiency ARC 30.2% #4 of 18
Math 6
FrontierMath Tiers 1–3 (v2) FrontierMath Tiers 1–3 (v2): Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 85.6% #12 of 69
FrontierMath Tier 4 (v2) FrontierMath Tier 4 (v2): Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 73.2% #11 of 54
MathArenaArXivMath · June 2026 MathArena · arxiv · 06/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 82.6% #9 of 24+2 versions & slices BrokenArXiv · June 2026 MathArena · arxiv_false · 06/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 90.7% #5 of 24ArXivLean · June 2026 MathArena · arxivlean · 06/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 32.6% #2 of 9
FrontierMath Erdos FrontierMath Erdos: Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 0% #6 of 13
Science 3
Humanity's Last Exam Humanity's Last Exam: Very hard expert questions across many fields, written to stump today’s models AA 51.3% #9 of 334
CritPt (physics) CritPt (physics): Research-level physics problems that need many careful reasoning steps AA 26.9% #16 of 321
Vals Science Index Vals Science Index: Scientific problem solving across the index’s component evaluations Vals 47.9% #6 of 18
Health & law 5 Leads on 2
Vals LegalBench Vals LegalBench: Legal reasoning and legal-language understanding on LegalBench Vals 87% #6 of 89
Vals MedScribe Vals MedScribe: Accuracy of clinical notes produced from consultation transcripts Vals 91% #4 of 80
Vals MedCode Vals MedCode: Medical coding accuracy on patient encounters Vals 63.6% #1 of 78
Vals Legal Research Bench Vals Legal Research Bench: Grounded legal research; a task passes only if all criteria pass Vals 55.3% #1 of 69
MLCR-AA MLCR-AA: Models synthesize long medical records; the headline credits concise answers judged both accurate and complete AA 56.1% #6 of 64
Documents 2
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 82% #27 of 273
GDP.pdfAA all-pass GDP.pdf · AA all-pass: Models reason over professional PDF documents; an attempt passes only when every atomic criterion passes 20% #25 of 133
Legacy · saturated or no longer reported 3
GPQA Diamond GPQA Diamond: Graduate-level biology, chemistry and physics questions that can’t be solved by a quick web search 91.9% #22 of 312+1 versions & slices Epoch GPQA Diamond · source setting 2: Models answer graduate-level science multiple-choice questions Epoch 93.9% #11 of 133
OTIS Mock AIME 20242025 OTIS Mock AIME 2024 2025: Models solve the stated OTIS mock AIME mathematics problems Epoch 98.9% #15 of 130
No benchmark matches
OpenGLM 5.3 Flashmax-9%-87%$0.28Defaults to max · Self-hosted+4
Kimi K3maxOpen-32%-9%$2.00Sampling parameters are fixed+3
Qwen3.8 27BxhighOpen-61%-54%$1.01Context: 1M → 262K+5
Muse Glimmer 30BhighOpen-64%-97%$0.058Context: 1M → 131K