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 21.4 #110 of 337
Knowledge 6
AA OmniscienceAccuracy AA Omniscience · Accuracy: Measures correct answers on the AA Omniscience factual knowledge test AA 30.8% #74 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 82.7% #188 of 321
AA Omniscience Index AA Omniscience Index: Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA -30.8 #152 of 321
IFBench (instructions) IFBench (instructions): Checks whether the model follows precise formatting and content instructions AA 78.8% #8 of 248
EQ-Bench3 EQ-Bench 3: Judge-rated responses to social and emotionally nuanced scenarios, scored through the source pairwise ranking EQ-Bench 1,413 #26 of 50
Mystery Game Puzzles Mystery Game Puzzles: Models choose the best move in puzzle positions from an undisclosed game Epoch 18% #42 of 64
Math 11
MathArenaAIME 2026 MathArena · AIME 2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 94.2% #18 of 24+9 versions & slices HMMT February 2026 MathArena · HMMT February 2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 87.9% #16 of 24Apex Shortlist MathArena · apex · Apex Shortlist: Answer accuracy on the named mathematics competition under the recorded effort MathArena 60.1% #19 of 30ArXivMath · December 2025 MathArena · arxiv · 12/2025: Answer accuracy on the named mathematics competition under the recorded effort MathArena 38.2% #10 of 13ArXivMath · January 2026 MathArena · arxiv · 01/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 54.9% #11 of 18Kangaroo 2025 1-2 MathArena · kangaroo · Kangaroo 2025 1-2: Answer accuracy on the named mathematics competition under the recorded effort MathArena 81.3% #7 of 17Kangaroo 2025 11-12 MathArena · kangaroo · Kangaroo 2025 11-12: Answer accuracy on the named mathematics competition under the recorded effort MathArena 91.7% #10 of 17Kangaroo 2025 3-4 MathArena · kangaroo · Kangaroo 2025 3-4: Answer accuracy on the named mathematics competition under the recorded effort MathArena 68.8% #6 of 17Kangaroo 2025 5-6 MathArena · kangaroo · Kangaroo 2025 5-6: Answer accuracy on the named mathematics competition under the recorded effort MathArena 74.9% #8 of 17USAMO 2026 MathArena · usamo · USAMO 2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 36.3% #7 of 8
FrontierMath Tiers 1–3 (v2) FrontierMath Tiers 1–3 (v2): Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 31.2% #57 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 29% #85 of 337
CritPt (physics) CritPt (physics): Research-level physics problems that need many careful reasoning steps AA 1.7% #112 of 324
SciCode SciCode: Writing code for real scientific computing problems (physics, biology, math) AA 44.8% #75 of 140
Coding 6
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 51.3% #69 of 156
ITBench SRE ITBench SRE: IT incident tasks: diagnose and fix broken systems like a site-reliability engineer AA 34.1% #25 of 37
WebDev Arena WebDev Arena: Human pairwise preferences in the stated webdev vote pool Arena 1,400 #69 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 1,400 #69 of 97
Terminal-Bench Hard Terminal-Bench Hard (version unstated): Agents solve difficult software, system-administration and data-processing tasks in a terminal AA 40.9% #32 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 6.9% #76 of 133
AA-Briefcase1.1 · Elo AA-Briefcase 1.1 · Elo: Agents produce professional deliverables; blind pairwise comparisons produce the source Elo rating AA 562 #92 of 140
APEX-Agents APEX-Agents: Agents complete long-horizon professional-services tasks across realistic applications AA 15.3% #20 of 29
EnterpriseOps-Gym-AA EnterpriseOps-Gym-AA: Agents complete stateful enterprise workflows in eight domains; final database state determines success AA 30.9% #34 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 14.6 #99 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 9.8% #20 of 21
τ³-BankingAA τ³-Banking · AA: Agents retrieve banking knowledge and execute tools to resolve customer-support workflows AA 13.4% #76 of 134
Multimodal 2
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 1,262 #39 of 88
Writing 17
Arena Textcreative writing Arena Text · creative writing: Human pairwise preferences in the stated text vote pool Arena 1,406 #61 of 195+14 versions & slices overall Arena Text · overall: Human pairwise preferences in the stated text vote pool Arena 1,442 #61 of 196Chinese Arena Text · chinese: Human pairwise preferences in the stated text vote pool Arena 1,499 #39 of 181English Arena Text · english: Human pairwise preferences in the stated text vote pool Arena 1,443 #59 of 188French Arena Text · french: Human pairwise preferences in the stated text vote pool Arena 1,461 #41 of 149German Arena Text · german: Human pairwise preferences in the stated text vote pool Arena 1,446 #41 of 154instruction following Arena Text · instruction following: Human pairwise preferences in the stated text vote pool Arena 1,423 #60 of 188Japanese Arena Text · japanese: Human pairwise preferences in the stated text vote pool Arena 1,429 #28 of 138Korean Arena Text · korean: Human pairwise preferences in the stated text vote pool Arena 1,383 #57 of 144non-English Arena Text · non english: Human pairwise preferences in the stated text vote pool Arena 1,430 #48 of 188Polish Arena Text · polish: Human pairwise preferences in the stated text vote pool Arena 1,449 #29 of 133Russian Arena Text · russian: Human pairwise preferences in the stated text vote pool Arena 1,429 #54 of 186Spanish Arena Text · spanish: Human pairwise preferences in the stated text vote pool Arena 1,441 #54 of 155overall · full cohort Arena Text · overall · snapshot 2026-10-15 · native board settings: Human pairwise preferences in the stated text vote pool Arena 1,438 #54 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 1,402 #59 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 68.3% #41 of 95
EQ-Bench Creative Writingv3 Creative Writing v3 · Elo: Judge-rated creative writing under the v3 prompt set and pairwise ranking EQ-Bench 1,478 #52 of 91
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 77.3% #76 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 12.2% #48 of 133
Legacy · saturated or no longer reported 14
GPQA Diamond GPQA Diamond: Graduate-level biology, chemistry and physics questions that can’t be solved by a quick web search 89.3% #44 of 315+1 versions & slices Epoch GPQA Diamond · source setting 2: Models answer graduate-level science multiple-choice questions Epoch 86.4% #51 of 133
τ²-benchairline · 1.0.1 τ-bench official · 2-airline-1.0.1: Customer-service agents converse with simulated users, retrieve domain knowledge and change state through tools Sierra 81.5% #5 of 6+4 versions & slices overall · 1.0.1 τ-bench official · 2-overall-1.0.1: Customer-service agents converse with simulated users, retrieve domain knowledge and change state through tools Sierra 87.9% #1 of 6retail · 1.0.1 τ-bench official · 2-retail-1.0.1: Customer-service agents converse with simulated users, retrieve domain knowledge and change state through tools Sierra 84.4% #1 of 6telecom · 1.0.1 τ-bench official · 2-telecom-1.0.1: Customer-service agents converse with simulated users, retrieve domain knowledge and change state through tools Sierra 97.8% #1 of 6AA τ²-Bench: Tests service agents that use tools while coordinating with a simulated user AA 95.6% #16 of 245
OTIS Mock AIME 20242025 OTIS Mock AIME 2024 2025: Models solve the stated OTIS mock AIME mathematics problems Epoch 88.9% #49 of 130
SWE-rebenchall · 2026-02-01 to 2026-03-01 SWE-rebench · all · 2026-02-01 to 2026-03-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 59.9% #2 of 5+5 versions & slices Go · 2026-02-01 to 2026-03-01 SWE-rebench · go · 2026-02-01 to 2026-03-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 5Java · 2026-02-01 to 2026-03-01 SWE-rebench · java · 2026-02-01 to 2026-03-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 5Python · 2026-02-01 to 2026-03-01 SWE-rebench · python · 2026-02-01 to 2026-03-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 59.9% #2 of 5Rust · 2026-02-01 to 2026-03-01 SWE-rebench · rust · 2026-02-01 to 2026-03-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 5TypeScript · 2026-02-01 to 2026-03-01 SWE-rebench · typescript · 2026-02-01 to 2026-03-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 5
No benchmark matches
CheaperGemini 3 Flash Previewhigh×2.8-17%$0.50 / $3
BetterGrok 4.5high×4.9+122%$0.88
OpenGLM 5.2xhigh×3.8+59%$1.40 / $4.40Memory (4-bit): 242 GB → 452 GB+1
BetterGPT-5.6 Solxhigh×4.8+493%$1.18
BetterMuse Spark 1.1xhigh×4.1+48%$1.38Only n=1 · Meta / Chat Completions+1
Kimi K3maxOpen×3.8+344%$2.00Memory (4-bit): 242 GB → 1,668 GB+4