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 11.6 #188 of 337
Knowledge 7
AA OmniscienceAccuracy AA Omniscience · Accuracy: Measures correct answers on the AA Omniscience factual knowledge test AA 21.8% #138 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 90.8% #256 of 321
AA Omniscience Index AA Omniscience Index: Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA -49.3 #206 of 321
IFBench (instructions) IFBench (instructions): Checks whether the model follows precise formatting and content instructions AA 69% #54 of 248
EQ-Bench3 EQ-Bench 3: Judge-rated responses to social and emotionally nuanced scenarios, scored through the source pairwise ranking EQ-Bench 1,076 #37 of 50
SimpleQA Verifiedv1 SimpleQA Verified v1: Accuracy on short factual questions with verified answers, answered without web access 13.1% #73 of 83
Mystery Game Puzzles Mystery Game Puzzles: Models choose the best move in puzzle positions from an undisclosed game Epoch 0% #64 of 64
Math 8
MathArenaAIME 2025 MathArena · aime · AIME 2025: Answer accuracy on the named mathematics competition under the recorded effort MathArena 90% #11 of 30+7 versions & slices Apex MathArena · apex · Apex: Answer accuracy on the named mathematics competition under the recorded effort MathArena 1% #25 of 34Apex Shortlist MathArena · apex · Apex Shortlist: Answer accuracy on the named mathematics competition under the recorded effort MathArena 45.2% #24 of 30BRUMO 2025 MathArena · brumo · BRUMO 2025: Answer accuracy on the named mathematics competition under the recorded effort MathArena 92.5% #9 of 24CMIMC 2025 MathArena · cmimc · CMIMC 2025: Answer accuracy on the named mathematics competition under the recorded effort MathArena 85% #9 of 22HMMT February 2025 MathArena · hmmt · HMMT Feb 2025: Answer accuracy on the named mathematics competition under the recorded effort MathArena 90% #8 of 30HMMT November 2025 MathArena · hmmt · HMMT Nov 2025: Answer accuracy on the named mathematics competition under the recorded effort MathArena 90% #6 of 14SMT 2025 MathArena · smt · SMT 2025: Answer accuracy on the named mathematics competition under the recorded effort MathArena 87.7% #10 of 24
Science 3
Humanity's Last Exam Humanity's Last Exam: Very hard expert questions across many fields, written to stump today’s models AA 19.6% #126 of 337
CritPt (physics) CritPt (physics): Research-level physics problems that need many careful reasoning steps AA 1.1% #120 of 324
SciCode SciCode: Writing code for real scientific computing problems (physics, biology, math) AA 34% #117 of 140
Coding 5
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 26.2% #105 of 156
DeepSWE1.1 DeepSWE 1.1: Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition 0% #41 of 44
ITBench SRE ITBench SRE: IT incident tasks: diagnose and fix broken systems like a site-reliability engineer AA 5.6% #36 of 37
Terminal-Bench Hard Terminal-Bench Hard (version unstated): Agents solve difficult software, system-administration and data-processing tasks in a terminal AA 23.5% #81 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 0.2% #130 of 133
AA-Briefcase1.1 · Elo AA-Briefcase 1.1 · Elo: Agents produce professional deliverables; blind pairwise comparisons produce the source Elo rating AA 0 #129 of 140
APEX-Agents APEX-Agents: Agents complete long-horizon professional-services tasks across realistic applications AA 3.1% #26 of 29
EnterpriseOps-Gym-AA EnterpriseOps-Gym-AA: Agents complete stateful enterprise workflows in eight domains; final database state determines success AA 25.5% #41 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 5.4 #114 of 175
τ³-BankingAA τ³-Banking · AA: Agents retrieve banking knowledge and execute tools to resolve customer-support workflows AA 12.8% #80 of 134
Writing 18
Arena Textcreative writing Arena Text · creative writing: Human pairwise preferences in the stated text vote pool Arena 1,279 #144 of 195+14 versions & slices overall Arena Text · overall: Human pairwise preferences in the stated text vote pool Arena 1,352 #121 of 196Chinese Arena Text · chinese: Human pairwise preferences in the stated text vote pool Arena 1,385 #112 of 181English Arena Text · english: Human pairwise preferences in the stated text vote pool Arena 1,375 #117 of 188French Arena Text · french: Human pairwise preferences in the stated text vote pool Arena 1,369 #102 of 149German Arena Text · german: Human pairwise preferences in the stated text vote pool Arena 1,354 #96 of 154instruction following Arena Text · instruction following: Human pairwise preferences in the stated text vote pool Arena 1,318 #122 of 188Japanese Arena Text · japanese: Human pairwise preferences in the stated text vote pool Arena 1,330 #78 of 138Korean Arena Text · korean: Human pairwise preferences in the stated text vote pool Arena 1,283 #101 of 144non-English Arena Text · non english: Human pairwise preferences in the stated text vote pool Arena 1,351 #107 of 188Polish Arena Text · polish: Human pairwise preferences in the stated text vote pool Arena 1,353 #91 of 133Russian Arena Text · russian: Human pairwise preferences in the stated text vote pool Arena 1,343 #110 of 186Spanish Arena Text · spanish: Human pairwise preferences in the stated text vote pool Arena 1,389 #92 of 155overall · full cohort Arena Text · overall · snapshot 2026-10-15 · native board settings: Human pairwise preferences in the stated text vote pool Arena 1,366 #109 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 1,275 #132 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 35.8% #81 of 95
EQ-Bench Creative Writingv3 Creative Writing v3 · Elo: Judge-rated creative writing under the v3 prompt set and pairwise ranking EQ-Bench 961 #77 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 -3.2 #41 of 44
Health & law 2
MLCR-AA MLCR-AA: Models synthesize long medical records; the headline credits concise answers judged both accurate and complete AA 1.1% #58 of 64
Vals LegalBench Vals LegalBench: Legal reasoning and legal-language understanding on LegalBench Vals 75.9% #74 of 89
Documents 2
GDP.pdfAA all-pass GDP.pdf · AA all-pass: Models reason over professional PDF documents; an attempt passes only when every atomic criterion passes 4% #91 of 133
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 52% #176 of 275
Legacy · saturated or no longer reported 20
AIME2025 · AA archived AIME 2025 · AA archived: AA evaluates the 30 integer-answer problems from the 2025 AIME mathematics competition AA 93.4% #10 of 140
LiveCodeBenchAA archived LiveCodeBench · AA archived: AA evaluates solutions to newly collected competitive-programming problems AA 87.8% #5 of 153
GPQA Diamond GPQA Diamond: Graduate-level biology, chemistry and physics questions that can’t be solved by a quick web search 78.2% #125 of 315+1 versions & slices Epoch GPQA Diamond · source setting 2: Models answer graduate-level science multiple-choice questions Epoch 75.8% #73 of 133
Aider Polyglottwo attempts Aider Polyglot · two attempts: Models edit code for 225 Exercism exercises in six languages, with a second attempt after test feedback Aider 41.8% #7 of 15
SWE-bench Pro (public) SWE-bench Pro (public): Agents resolve long-horizon professional repository tasks; public and private splits are separate 16.2% #16 of 19
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 · 2025-08-01 to 2026-03-01 SWE-rebench · all · 2025-08-01 to 2026-03-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 27.3% #2 of 2+11 versions & slices all · 2025-12-01 to 2026-01-01 SWE-rebench · all · 2025-12-01 to 2026-01-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 37% #1 of 1Go · 2025-08-01 to 2026-03-01 SWE-rebench · go · 2025-08-01 to 2026-03-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 2Go · 2025-12-01 to 2026-01-01 SWE-rebench · go · 2025-12-01 to 2026-01-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 1Java · 2025-08-01 to 2026-03-01 SWE-rebench · java · 2025-08-01 to 2026-03-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 2Java · 2025-12-01 to 2026-01-01 SWE-rebench · java · 2025-12-01 to 2026-01-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 1Python · 2025-08-01 to 2026-03-01 SWE-rebench · python · 2025-08-01 to 2026-03-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 27.3% #2 of 2Python · 2025-12-01 to 2026-01-01 SWE-rebench · python · 2025-12-01 to 2026-01-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 37% #1 of 1Rust · 2025-08-01 to 2026-03-01 SWE-rebench · rust · 2025-08-01 to 2026-03-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 2Rust · 2025-12-01 to 2026-01-01 SWE-rebench · rust · 2025-12-01 to 2026-01-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 1TypeScript · 2025-08-01 to 2026-03-01 SWE-rebench · typescript · 2025-08-01 to 2026-03-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 2TypeScript · 2025-12-01 to 2026-01-01 SWE-rebench · typescript · 2025-12-01 to 2026-01-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 1
τ²-benchAA τ²-Bench: Tests service agents that use tools while coordinating with a simulated user AA 65.8% #98 of 245
No benchmark matches
CheaperMiMo v2.5 ProthinkingOpen+16%-41%$0.054Memory (4-bit): 70 GB → 614 GB
BetterNemotron 3 Nano 30B A3BthinkingOpen+3%-82%$0.017
CheaperGemini 3.1 Flash Litehigh+12%-35%$0.06
Solar Pro 3high+3%-14%$0.079
MiniMax M2.7thinkingOpen+10%+775%$0.30 / $1.20Memory (4-bit): 70 GB → 137 GB
Qwen 3.5 122B A10BthinkingOpen+10%+252%$0.32Memory (4-bit): 70 GB → 75 GB