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 20 #121 of 337
Knowledge 4
AA OmniscienceAccuracy AA Omniscience · Accuracy: Measures correct answers on the AA Omniscience factual knowledge test AA 21.9% #136 of 321+1 versions & slices Hallucination Rate AA Omniscience · Hallucination Rate: Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test AA 51.1% #92 of 321
AA Omniscience Index AA Omniscience Index: Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA -18 #119 of 321
IFBench (instructions) IFBench (instructions): Checks whether the model follows precise formatting and content instructions AA 64.4% #72 of 248
Reasoning 4
ARC-AGI-1public evaluation ARC-AGI-1 · public-eval: Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 43.4% #51 of 61+1 versions & slices semi-private ARC-AGI-1 · semi-private: Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 33% #53 of 64
ARC-AGI-2public evaluation ARC-AGI-2 · public-eval: Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 3.5% #51 of 63+1 versions & slices semi-private ARC-AGI-2 · semi-private: Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 1.9% #56 of 66
Science 3
Humanity's Last Exam Humanity's Last Exam: Very hard expert questions across many fields, written to stump today’s models AA 15.9% #139 of 337
CritPt (physics) CritPt (physics): Research-level physics problems that need many careful reasoning steps AA 5.1% #78 of 324
SciCode SciCode: Writing code for real scientific computing problems (physics, biology, math) AA 47.2% #64 of 140
Coding 4
Terminal-Bench4.0 Terminal-Bench 4.0 · source setting 2: Agents use a terminal to complete executable coding, system administration and research tasks in the 4.0 suite 0.5% #63 of 132+1 versions & slices 2.1 Terminal-Bench 2.1 · source setting 2: Older, easier version of Terminal-Bench; Still widely reported AA 60.7% #53 of 156
ITBench SRE ITBench SRE: IT incident tasks: diagnose and fix broken systems like a site-reliability engineer AA 24.4% #33 of 37
Terminal-Bench Hard Terminal-Bench Hard (version unstated): Agents solve difficult software, system-administration and data-processing tasks in a terminal AA 33.3% #50 of 242
Agents 6
AutomationBench-AA AutomationBench-AA: Agents orchestrate SaaS workflows through APIs; objectives receive credit only when the task has no guardrail violation AA 6% #81 of 133
AA-Briefcase1.1 · Elo AA-Briefcase 1.1 · Elo: Agents produce professional deliverables; blind pairwise comparisons produce the source Elo rating AA 674 #86 of 140
APEX-Agents APEX-Agents: Agents complete long-horizon professional-services tasks across realistic applications AA 24.9% #17 of 29
EnterpriseOps-Gym-AA EnterpriseOps-Gym-AA: Agents complete stateful enterprise workflows in eight domains; final database state determines success AA 31.5% #33 of 43
GDPval-AA (work tasks)2.1 GDPval-AA (work tasks) 2.1: Real work tasks from many professions (reports, spreadsheets, analyses), graded against expert work AA 22.4 #87 of 175
τ³-BankingAA τ³-Banking · AA: Agents retrieve banking knowledge and execute tools to resolve customer-support workflows AA 27.4% #39 of 134
Multimodal 2
MMMU-Pro (vision) MMMU-Pro (vision): College-level questions that require understanding images: charts, diagrams, photos AA 59.5% #98 of 127
Arena Vision Arena Vision · overall: Human pairwise preferences in the stated vision vote pool Arena 1,196 #66 of 88
Writing 16
Arena Textcreative writing Arena Text · creative writing: Human pairwise preferences in the stated text vote pool Arena 1,337 #109 of 195+14 versions & slices overall Arena Text · overall: Human pairwise preferences in the stated text vote pool Arena 1,401 #98 of 196Chinese Arena Text · chinese: Human pairwise preferences in the stated text vote pool Arena 1,391 #109 of 181English Arena Text · english: Human pairwise preferences in the stated text vote pool Arena 1,381 #108 of 188French Arena Text · french: Human pairwise preferences in the stated text vote pool Arena 1,396 #94 of 149German Arena Text · german: Human pairwise preferences in the stated text vote pool Arena 1,368 #87 of 154instruction following Arena Text · instruction following: Human pairwise preferences in the stated text vote pool Arena 1,362 #101 of 188Japanese Arena Text · japanese: Human pairwise preferences in the stated text vote pool Arena 1,343 #72 of 138Korean Arena Text · korean: Human pairwise preferences in the stated text vote pool Arena 1,321 #86 of 144non-English Arena Text · non english: Human pairwise preferences in the stated text vote pool Arena 1,359 #103 of 188Polish Arena Text · polish: Human pairwise preferences in the stated text vote pool Arena 1,365 #87 of 133Russian Arena Text · russian: Human pairwise preferences in the stated text vote pool Arena 1,362 #102 of 186Spanish Arena Text · spanish: Human pairwise preferences in the stated text vote pool Arena 1,371 #103 of 155overall · full cohort Arena Text · overall · snapshot 2026-10-15 · native board settings: Human pairwise preferences in the stated text vote pool Arena 1,372 #105 of 188creative writing · full cohort Arena Text · creative writing · snapshot 2026-10-15 · native board settings: Human pairwise preferences in the stated text vote pool Arena 1,314 #115 of 187
EQ-Bench Longform Creative Writing1.11 Longform Creative Writing 1.11: Models plan, revise and write a story across eight turns, graded with a writing rubric EQ-Bench 57.8% #54 of 95
Health & law 5
MLCR-AA MLCR-AA: Models synthesize long medical records; the headline credits concise answers judged both accurate and complete AA 5% #50 of 64
Vals LegalBench Vals LegalBench: Legal reasoning and legal-language understanding on LegalBench Vals 77.9% #71 of 89
Vals MedCode Vals MedCode: Medical coding accuracy on patient encounters Vals 41% #48 of 78
Vals MedScribe Vals MedScribe: Accuracy of clinical notes produced from consultation transcripts Vals 77.1% #55 of 80
Vals Legal Research Bench Vals Legal Research Bench: Grounded legal research; a task passes only if all criteria pass Vals 6.3% #64 of 69
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 67.3% #135 of 275
GDP.pdfAA all-pass GDP.pdf · AA all-pass: Models reason over professional PDF documents; an attempt passes only when every atomic criterion passes 7.8% #70 of 133
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 76.1% #143 of 315
τ²-benchAA τ²-Bench: Tests service agents that use tools while coordinating with a simulated user AA 52.6% #110 of 245
No benchmark matches
CheaperClaude Haiku 5.5max×2.2-57%$0.21Remove sampling parameters+5
OpenMiMo v2.6 Prothinking×2.3+18%$0.13Pass back reasoning_content+3
CheaperMiniMax M3.1 Flashthinking×2.1-43%$0.22Complete model response must be appended
CheaperGLM 5.3 FlashmaxOpen×2.1-49%$0.28Defaults to max · Self-hosted+4
Qwen3.8 FlashthinkingOpen+99%-50%$0.37Context: 400K → 262K+6
DeepSeek V4.1 Flash 1017maxOpen×2.3+14%$0.26Pass back reasoning_content · Chat Completions+4
Step 5 PreviewthinkingOpen×2.2+208%$1.03web_search not available · Chat Completions+2
Kimi K3maxOpen×2.2+1,197%$2.00Sampling parameters are fixed+3