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 16.9 #135 of 337
Knowledge 5
AA OmniscienceAccuracy AA Omniscience · Accuracy: Measures correct answers on the AA Omniscience factual knowledge test AA 18% #184 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 27.3% #26 of 321
AA Omniscience Index AA Omniscience Index: Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA -4.4 #81 of 321
IFBench (instructions) IFBench (instructions): Checks whether the model follows precise formatting and content instructions AA 54.3% #104 of 248
SimpleQA Verifiedv1 SimpleQA Verified v1: Accuracy on short factual questions with verified answers, answered without web access 13.2% #72 of 83
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 62.9% #46 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 47.7% #51 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 5.1% #47 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 4% #54 of 66
Math 3
AA Analyst Agent AA Analyst Agent: Data-analyst tasks: the model explores data with tools and reports findings AA 15% #35 of 43
FrontierMath FrontierMath: Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 4.1% #33 of 40
MATH Level5 MATH Level 5: Models solve competition mathematics problems from the hardest MATH difficulty level Epoch 86.9% #8 of 35
Science 3
Humanity's Last Exam Humanity's Last Exam: Very hard expert questions across many fields, written to stump today’s models AA 10.4% #186 of 337
CritPt (physics) CritPt (physics): Research-level physics problems that need many careful reasoning steps AA 0% #180 of 324
SciCode SciCode: Writing code for real scientific computing problems (physics, biology, math) AA 42.2% #85 of 140
Coding 8
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% #75 of 132+1 versions & slices 2.1 Terminal-Bench 2.1 · source setting 2: Older, easier version of Terminal-Bench; Still widely reported AA 44.2% #78 of 156
ITBench SRE ITBench SRE: IT incident tasks: diagnose and fix broken systems like a site-reliability engineer AA 27.3% #31 of 37
WebDev Arena WebDev Arena: Human pairwise preferences in the stated webdev vote pool Arena 1,330 #84 of 97+1 versions & slices full cohort WebDev Arena · snapshot 2026-10-19 · native board settings: Human pairwise preferences in the stated webdev vote pool Arena 1,330 #84 of 97
SWE-bench Pro (v2 hard) SWE-bench Pro (v2 hard): Agents resolve repository issues under the network-locked v2 protocol; full and 51-task Hard results are separate Scale 25.5% #16 of 16
DeepSWE1 DeepSWE 1: Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition Datacurve 0.2% #19 of 20
Terminal-Bench Hard Terminal-Bench Hard (version unstated): Agents solve difficult software, system-administration and data-processing tasks in a terminal AA 27.3% #67 of 242
Agents 7
AutomationBench-AA AutomationBench-AA: Agents orchestrate SaaS workflows through APIs; objectives receive credit only when the task has no guardrail violation AA 3.2% #90 of 133
AA-Briefcase1.1 · Elo AA-Briefcase 1.1 · Elo: Agents produce professional deliverables; blind pairwise comparisons produce the source Elo rating AA 616 #90 of 140
EnterpriseOps-Gym-AA EnterpriseOps-Gym-AA: Agents complete stateful enterprise workflows in eight domains; final database state determines success AA 29.4% #35 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 11.6 #108 of 175
MCP-Atlas Public MCPAtlas Public: MCPAtlas Public as reported in this launch evaluation; the post is the authority for the recorded task and grading scope 41.2% #16 of 16
MCP-Atlasfull 1000 MCP-Atlas · full 1000: Tool orchestration across MCP servers on the stated task split Scale 40.2% #16 of 16
τ³-BankingAA τ³-Banking · AA: Agents retrieve banking knowledge and execute tools to resolve customer-support workflows AA 9.3% #95 of 134
Multimodal 1
MMMU-Pro (vision) MMMU-Pro (vision): College-level questions that require understanding images: charts, diagrams, photos AA 58.6% #100 of 127
Writing 16
Arena Textcreative writing Arena Text · creative writing: Human pairwise preferences in the stated text vote pool Arena 1,388 #80 of 195+14 versions & slices overall Arena Text · overall: Human pairwise preferences in the stated text vote pool Arena 1,414 #88 of 196Chinese Arena Text · chinese: Human pairwise preferences in the stated text vote pool Arena 1,418 #98 of 181English Arena Text · english: Human pairwise preferences in the stated text vote pool Arena 1,414 #88 of 188French Arena Text · french: Human pairwise preferences in the stated text vote pool Arena 1,409 #85 of 149German Arena Text · german: Human pairwise preferences in the stated text vote pool Arena 1,374 #83 of 154instruction following Arena Text · instruction following: Human pairwise preferences in the stated text vote pool Arena 1,414 #68 of 188Japanese Arena Text · japanese: Human pairwise preferences in the stated text vote pool Arena 1,338 #74 of 138Korean Arena Text · korean: Human pairwise preferences in the stated text vote pool Arena 1,346 #79 of 144non-English Arena Text · non english: Human pairwise preferences in the stated text vote pool Arena 1,377 #97 of 188Polish Arena Text · polish: Human pairwise preferences in the stated text vote pool Arena 1,342 #97 of 133Russian Arena Text · russian: Human pairwise preferences in the stated text vote pool Arena 1,381 #93 of 186Spanish Arena Text · spanish: Human pairwise preferences in the stated text vote pool Arena 1,421 #71 of 155overall · full cohort Arena Text · overall · snapshot 2026-10-15 · native board settings: Human pairwise preferences in the stated text vote pool Arena 1,397 #94 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 1,371 #82 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 65% #47 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 6.1% #48 of 64
Vals LegalBench Vals LegalBench: Legal reasoning and legal-language understanding on LegalBench Vals 81.2% #60 of 89
Vals MedCode Vals MedCode: Medical coding accuracy on patient encounters Vals 32.7% #66 of 78
Vals MedScribe Vals MedScribe: Accuracy of clinical notes produced from consultation transcripts Vals 85.2% #28 of 80
Vals Legal Research Bench Vals Legal Research Bench: Grounded legal research; a task passes only if all criteria pass Vals 10.6% #60 of 69
Documents 3
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 74.3% #93 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 3.8% #94 of 133
Arena Document Arena Document · overall: Human pairwise preferences in the stated document vote pool Arena 1,420 #29 of 33
Legacy · saturated or no longer reported 9
AIME2025 · AA archived AIME 2025 · AA archived: AA evaluates the 30 integer-answer problems from the 2025 AIME mathematics competition AA 83.7% #34 of 140
LiveCodeBenchAA archived LiveCodeBench · AA archived: AA evaluates solutions to newly collected competitive-programming problems AA 61.5% #72 of 153
GPQA Diamond GPQA Diamond: Graduate-level biology, chemistry and physics questions that can’t be solved by a quick web search 67.2% #201 of 315+1 versions & slices Epoch GPQA Diamond · source setting 2: Models answer graduate-level science multiple-choice questions Epoch 60.5% #94 of 133
BFCLv4 BFCL v4: Tests function calling, multi-turn interactions, search and memory in the v4 suite Berkeley 68.7% #3 of 39+1 versions & slices v4 · prompt mode BFCL v4 · BFCL v4 source function-call format · historical run: Tests function calling, multi-turn interactions, search and memory in the v4 suite Berkeley 25.3% #14 of 16
SWE-bench Pro (public) SWE-bench Pro (public): Agents resolve long-horizon professional repository tasks; public and private splits are separate 39.5% #10 of 19
OTIS Mock AIME 20242025 OTIS Mock AIME 2024 2025: Models solve the stated OTIS mock AIME mathematics problems Epoch 35.8% #99 of 130
τ²-benchAA τ²-Bench: Tests service agents that use tools while coordinating with a simulated user AA 54.7% #106 of 245
No benchmark matches
BetterMuse Glimmer 30BhighOpen+18%-79%$0.058Context: 200K → 131K
OpenDeepSeek V4 Pro 0813max+69%+143%$0.67No image input+5
CheaperGemini 3.5 Flash Litehigh+44%-30%$0.19
CheaperGPT-5.6 Lunamax+39%-36%$0.18
Qwen3.7 Plusthinking+38%-22%$0.22TInklingxhighOpen+29%-14%$0.95 / $4.05No strict JSON
Step 5 PreviewthinkingOpen+61%+271%$1.03web_search not available · Chat Completions+2
Kimi K3maxOpen+54%+623%$2.00Sampling parameters are fixed+3