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 #19 of 337
Knowledge 6
AA OmniscienceAccuracy AA Omniscience · Accuracy: Measures correct answers on the AA Omniscience factual knowledge test AA 58.8% #7 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 91.9% #272 of 321
AA Omniscience Index AA Omniscience Index: Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA 21 #24 of 321
IFBench (instructions) IFBench (instructions): Checks whether the model follows precise formatting and content instructions AA 71% #46 of 248
SimpleQA Verifiedv1 SimpleQA Verified v1: Accuracy on short factual questions with verified answers, answered without web access 69.7% #9 of 83
Mystery Game Puzzles Mystery Game Puzzles: Models choose the best move in puzzle positions from an undisclosed game Epoch 58% #7 of 64
Reasoning 6
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 98.8% #5 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 97.5% #8 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 91.9% #10 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 90% #6 of 66
ARC-AGI-3semi-private ARC-AGI-3 · semi-private: Measures interactive game solving through relative human action efficiency ARC 7% #6 of 18
Chess Puzzles Chess Puzzles: Models choose the best next move from a novel chess position Epoch 59% #6 of 68
Math 6
AA Analyst Agent AA Analyst Agent: Data-analyst tasks: the model explores data with tools and reports findings AA 47.5% #12 of 43
FrontierMath Erdos FrontierMath Erdos: Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 0% #6 of 13
FrontierMath Tier 4 (v2) FrontierMath Tier 4 (v2): Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 82.9% #7 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 89.1% #6 of 69
MathArenaArXivMath · June 2026 MathArena · arxiv · 06/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 88.5% #5 of 24+1 versions & slices BrokenArXiv · June 2026 MathArena · arxiv_false · 06/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 67.3% #8 of 24
Science 5
Humanity's Last Exam Humanity's Last Exam: Very hard expert questions across many fields, written to stump today’s models AA 47.3% #17 of 337
CritPt (physics) CritPt (physics): Research-level physics problems that need many careful reasoning steps AA 28.6% #12 of 324
Vals Science Index Vals Science Index: Scientific problem solving across the index’s component evaluations Vals 41.5% #8 of 18
SciCode SciCode: Writing code for real scientific computing problems (physics, biology, math) AA 57.1% #19 of 140
Terminal-Bench Science0.1 Terminal-Bench Science 0.1: Agents complete expert-authored research workflows across five scientific domains in a terminal AA 22.4% #9 of 33
Coding 8 Leads on 1
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 24.7% #26 of 132+1 versions & slices 2.1 Terminal-Bench 2.1 · source setting 2: Older, easier version of Terminal-Bench; Still widely reported AA 89.5% #3 of 156
DeepSWE1.1 DeepSWE 1.1: Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition 70.7% #6 of 44
ITBench SRE ITBench SRE: IT incident tasks: diagnose and fix broken systems like a site-reliability engineer AA 56.2% #1 of 37
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 95.5% #10 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 82.4% #10 of 16
MirrorCode MirrorCode: Agents reimplement software projects by observing their behavior Epoch 20% #6 of 9
Terminal-Bench Hard Terminal-Bench Hard (version unstated): Agents solve difficult software, system-administration and data-processing tasks in a terminal AA 61.4% #3 of 242
Agents 8
AutomationBench-AA AutomationBench-AA: Agents orchestrate SaaS workflows through APIs; objectives receive credit only when the task has no guardrail violation AA 55.3% #30 of 133
AA-Briefcase1.1 · Elo AA-Briefcase 1.1 · Elo: Agents produce professional deliverables; blind pairwise comparisons produce the source Elo rating AA 1,437 #25 of 140
EnterpriseOps-Gym-AA EnterpriseOps-Gym-AA: Agents complete stateful enterprise workflows in eight domains; final database state determines success AA 42.9% #15 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 53.4 #25 of 175
τ³-benchbanking · 1.0.1 τ-bench official · 3-banking-1.0.1: Customer-service agents converse with simulated users, retrieve domain knowledge and change state through tools Sierra 46.9% #3 of 21
EBR Bench EBR Bench: Agents learn to play Earthborne Rangers across repeated playthroughs Epoch 44.8% #8 of 24
Furniture Assembly Furniture Assembly: Models inspect furniture assembly photos, identify incorrect builds and locate the mistaken step Epoch 56.7% #9 of 31
τ³-BankingAA τ³-Banking · AA: Agents retrieve banking knowledge and execute tools to resolve customer-support workflows AA 38.1% #20 of 134
Multimodal 3
MMMU-Pro (vision) MMMU-Pro (vision): College-level questions that require understanding images: charts, diagrams, photos AA 82.7% #9 of 127
Arena Vision Arena Vision · overall: Human pairwise preferences in the stated vision vote pool Arena 1,281 #24 of 88
Chartography Chartography: Expert chart reasoning over professional scientific, medical, financial and engineering charts Surge 45% #6 of 37
Writing 18
Arena Textcreative writing Arena Text · creative writing: Human pairwise preferences in the stated text vote pool Arena 1,469 #12 of 195+14 versions & slices overall Arena Text · overall: Human pairwise preferences in the stated text vote pool Arena 1,485 #16 of 196Chinese Arena Text · chinese: Human pairwise preferences in the stated text vote pool Arena 1,527 #20 of 181English Arena Text · english: Human pairwise preferences in the stated text vote pool Arena 1,458 #37 of 188French Arena Text · french: Human pairwise preferences in the stated text vote pool Arena 1,474 #26 of 149German Arena Text · german: Human pairwise preferences in the stated text vote pool Arena 1,476 #16 of 154instruction following Arena Text · instruction following: Human pairwise preferences in the stated text vote pool Arena 1,482 #13 of 188Japanese Arena Text · japanese: Human pairwise preferences in the stated text vote pool Arena 1,471 #14 of 138Korean Arena Text · korean: Human pairwise preferences in the stated text vote pool Arena 1,442 #17 of 144non-English Arena Text · non english: Human pairwise preferences in the stated text vote pool Arena 1,451 #28 of 188Polish Arena Text · polish: Human pairwise preferences in the stated text vote pool Arena 1,461 #20 of 133Russian Arena Text · russian: Human pairwise preferences in the stated text vote pool Arena 1,470 #22 of 186Spanish Arena Text · spanish: Human pairwise preferences in the stated text vote pool Arena 1,441 #53 of 155overall · full cohort Arena Text · overall · snapshot 2026-10-15 · native board settings: Human pairwise preferences in the stated text vote pool Arena 1,457 #32 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 1,449 #24 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 81.7% #12 of 95
EQ-Bench Creative Writingv3 Creative Writing v3 · Elo: Judge-rated creative writing under the v3 prompt set and pairwise ranking EQ-Bench 1,972 #9 of 91
Lech Mazur Short-Story Lech Mazur Short-Story · comparison score: Judges compare stories written to ten required elements; the comparison score can be negative Lech 2.5 #7 of 44
Health & law 5
MLCR-AA MLCR-AA: Models synthesize long medical records; the headline credits concise answers judged both accurate and complete AA 18.3% #24 of 64
Vals LegalBench Vals LegalBench: Legal reasoning and legal-language understanding on LegalBench Vals 87% #6 of 89
Vals MedCode Vals MedCode: Medical coding accuracy on patient encounters Vals 44% #35 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 48.1% #8 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 82.3% #25 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 27.6% #7 of 133
Arena Document Arena Document · overall: Human pairwise preferences in the stated document vote pool Arena 1,483 #7 of 33
Legacy · saturated or no longer reported 10
GPQA Diamond GPQA Diamond: Graduate-level biology, chemistry and physics questions that can’t be solved by a quick web search 93.1% #11 of 315+1 versions & slices Epoch GPQA Diamond · source setting 2: Models answer graduate-level science multiple-choice questions Epoch 93.5% #12 of 133
OTIS Mock AIME 20242025 OTIS Mock AIME 2024 2025: Models solve the stated OTIS mock AIME mathematics problems Epoch 100% #1 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 62.3% #4 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 70.5% #3 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 57.1% #2 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 48% #5 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 68% #1 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 65.8% #4 of 6
τ²-benchAA τ²-Bench: Tests service agents that use tools while coordinating with a simulated user AA 84.8% #64 of 245
No benchmark matches
BetterMiMo v2.6 ProthinkingOpen+4%-89%$0.13Context: 1.05M → 1M+4
CheaperClaude Opus 5.5low+2%-53%$0.55Context: 1.05M → 1M+6
MiniMax M3.1 Flashthinkingsame-81%$0.22Context: 1.05M → 1M+1
Gemini 4 Argonhigh+21%+68%*$1.99Context: 1.05M → 1M+3
Kimi K3maxOpensame+69%$2.00Context: 1.05M → 1M+4
Step 5 PreviewthinkingOpensame-13%$1.03Context: 1.05M → 1M+3
Muse Spark OpenxhighOpen-7%-29%$0.84Context: 1.05M → 1M+2
DeepSeek V4.1 Flash 1017maxOpen-8%-78%$0.26Context: 1.05M → 1M+5