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 34.4 #43 of 337
Knowledge 5
AA OmniscienceAccuracy AA Omniscience · Accuracy: Measures correct answers on the AA Omniscience factual knowledge test AA 39% #50 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 58.6% #104 of 321
AA Omniscience Index AA Omniscience Index: Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA 3.2 #58 of 321
SimpleQA Verifiedv1 SimpleQA Verified v1: Accuracy on short factual questions with verified answers, answered without web access 32.9% #54 of 83
Mystery Game Puzzles Mystery Game Puzzles: Models choose the best move in puzzle positions from an undisclosed game Epoch 35% #17 of 64
Reasoning 1
Chess Puzzles Chess Puzzles: Models choose the best next move from a novel chess position Epoch 34% #38 of 68
Math 3
AA Analyst Agent AA Analyst Agent: Data-analyst tasks: the model explores data with tools and reports findings AA 46.3% #13 of 43
FrontierMath Tier 4 (v2) FrontierMath Tier 4 (v2): Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 29.3% #29 of 54
FrontierMath Tiers 1–3 (v2) FrontierMath Tiers 1–3 (v2): Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 65.6% #30 of 69
Science 3
Humanity's Last Exam Humanity's Last Exam: Very hard expert questions across many fields, written to stump today’s models AA 39% #48 of 337
CritPt (physics) CritPt (physics): Research-level physics problems that need many careful reasoning steps AA 15.4% #42 of 324
SciCode SciCode: Writing code for real scientific computing problems (physics, biology, math) AA 54.1% #33 of 140
Coding 7
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 7.1% #40 of 132+1 versions & slices 2.1 Terminal-Bench 2.1 · source setting 2: Older, easier version of Terminal-Bench; Still widely reported AA 80.5% #21 of 156
DeepSWE1.1 DeepSWE 1.1: Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition 49.7% #26 of 44
WebDev Arena WebDev Arena: Human pairwise preferences in the stated webdev vote pool Arena 1,540 #38 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 1,540 #38 of 97
SWE-bench Pro (v2 full) SWE-bench Pro (v2 full): Agents resolve repository issues under the network-locked v2 protocol; full and 51-task Hard results are separate Scale 93.2% #13 of 16
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 88.2% #6 of 16
Agents 5
AutomationBench-AA AutomationBench-AA: Agents orchestrate SaaS workflows through APIs; objectives receive credit only when the task has no guardrail violation AA 34.5% #48 of 133
AA-Briefcase1.1 · Elo AA-Briefcase 1.1 · Elo: Agents produce professional deliverables; blind pairwise comparisons produce the source Elo rating AA 1,273 #39 of 140
EnterpriseOps-Gym-AA EnterpriseOps-Gym-AA: Agents complete stateful enterprise workflows in eight domains; final database state determines success AA 43.9% #14 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 42.9 #41 of 175
τ³-BankingAA τ³-Banking · AA: Agents retrieve banking knowledge and execute tools to resolve customer-support workflows AA 37.3% #22 of 134
Multimodal 3
MMMU-Pro (vision) MMMU-Pro (vision): College-level questions that require understanding images: charts, diagrams, photos AA 77.3% #36 of 127
Arena Vision Arena Vision · overall: Human pairwise preferences in the stated vision vote pool Arena 1,273 #28 of 88
Chartography Chartography: Expert chart reasoning over professional scientific, medical, financial and engineering charts Surge 16.6% #25 of 37
Writing 17
Arena Textcreative writing Arena Text · creative writing: Human pairwise preferences in the stated text vote pool Arena 1,436 #40 of 195+14 versions & slices overall Arena Text · overall: Human pairwise preferences in the stated text vote pool Arena 1,461 #38 of 196Chinese Arena Text · chinese: Human pairwise preferences in the stated text vote pool Arena 1,478 #57 of 181English Arena Text · english: Human pairwise preferences in the stated text vote pool Arena 1,450 #48 of 188French Arena Text · french: Human pairwise preferences in the stated text vote pool Arena 1,464 #40 of 149German Arena Text · german: Human pairwise preferences in the stated text vote pool Arena 1,442 #44 of 154instruction following Arena Text · instruction following: Human pairwise preferences in the stated text vote pool Arena 1,452 #36 of 188Japanese Arena Text · japanese: Human pairwise preferences in the stated text vote pool Arena 1,425 #31 of 138Korean Arena Text · korean: Human pairwise preferences in the stated text vote pool Arena 1,413 #34 of 144non-English Arena Text · non english: Human pairwise preferences in the stated text vote pool Arena 1,431 #45 of 188Polish Arena Text · polish: Human pairwise preferences in the stated text vote pool Arena 1,426 #52 of 133Russian Arena Text · russian: Human pairwise preferences in the stated text vote pool Arena 1,450 #36 of 186Spanish Arena Text · spanish: Human pairwise preferences in the stated text vote pool Arena 1,437 #57 of 155overall · full cohort Arena Text · overall · snapshot 2026-10-15 · native board settings: Human pairwise preferences in the stated text vote pool Arena 1,442 #47 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 1,417 #47 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 78.3% #18 of 95
EQ-Bench Creative Writingv3 Creative Writing v3 · Elo: Judge-rated creative writing under the v3 prompt set and pairwise ranking EQ-Bench 1,794 #26 of 91
Health & law 5
MLCR-AA MLCR-AA: Models synthesize long medical records; the headline credits concise answers judged both accurate and complete AA 55% #7 of 64
Vals LegalBench Vals LegalBench: Legal reasoning and legal-language understanding on LegalBench Vals 83.9% #41 of 89
Vals MedCode Vals MedCode: Medical coding accuracy on patient encounters Vals 47.5% #27 of 78
Vals MedScribe Vals MedScribe: Accuracy of clinical notes produced from consultation transcripts Vals 76.1% #60 of 80
Vals Legal Research Bench Vals Legal Research Bench: Grounded legal research; a task passes only if all criteria pass Vals 41.8% #21 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 76.7% #80 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 12.6% #46 of 133
Arena Document Arena Document · overall: Human pairwise preferences in the stated document vote pool Arena 1,466 #14 of 33
Legacy · saturated or no longer reported 9
GPQA Diamond GPQA Diamond: Graduate-level biology, chemistry and physics questions that can’t be solved by a quick web search 91.1% #27 of 315+1 versions & slices Epoch GPQA Diamond · source setting 2: Models answer graduate-level science multiple-choice questions Epoch 90.5% #30 of 133
OTIS Mock AIME 20242025 OTIS Mock AIME 2024 2025: Models solve the stated OTIS mock AIME mathematics problems Epoch 94.7% #35 of 130
SWE-rebenchall · 2026-05-15 to 2026-07-01 SWE-rebench · all · 2026-05-15 to 2026-07-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 56.8% #5 of 6+5 versions & slices Go · 2026-05-15 to 2026-07-01 SWE-rebench · go · 2026-05-15 to 2026-07-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 66.7% #5 of 6Java · 2026-05-15 to 2026-07-01 SWE-rebench · java · 2026-05-15 to 2026-07-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 49.5% #4 of 6Python · 2026-05-15 to 2026-07-01 SWE-rebench · python · 2026-05-15 to 2026-07-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 53% #3 of 6Rust · 2026-05-15 to 2026-07-01 SWE-rebench · rust · 2026-05-15 to 2026-07-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 57.6% #5 of 6TypeScript · 2026-05-15 to 2026-07-01 SWE-rebench · typescript · 2026-05-15 to 2026-07-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 56.7% #5 of 6
No benchmark matches
BetterMiMo v2.6 FlashthinkingOpen+10%-98%$0.062Pass back reasoning_content+3
CheaperGemini 4 Argonhigh+53%-31%*$1.99Synchronous output stops at 65,536+2
GPT-6 Astraxhigh+52%-20%$2.31Monitoring can return HTTP 403+2
DeepSeek V4.1 Flash 1017maxOpen+31%-91%$0.26Pass back reasoning_content · Chat Completions+4
GLM 5.3maxOpen+30%-30%$2.01No image input+4
Step 5 PreviewthinkingOpen+27%-64%$1.03web_search not available · Chat Completions+2
Kimi K3maxOpen+27%-30%$2.00Sampling parameters are fixed+3