Benchmark By Score Rank
Overall 1
AA Intelligence Index4.3.2 Artificial Analysis combines tests of knowledge, reasoning, coding and tool use into one score AA 50.8 #9 of 337
Knowledge 5
AA OmniscienceAccuracy Measures correct answers on the AA Omniscience factual knowledge test AA 60.9% #6 of 321+1 versions & slices Hallucination Rate Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test AA 60.8% #107 of 321
AA Omniscience Index Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA 37.1 #7 of 321
SimpleQA Verifiedv1 Accuracy on short factual questions with verified answers, answered without web access 59.9% #15 of 83
Mystery Game Puzzles Models choose the best move in puzzle positions from an undisclosed game Epoch 59% #6 of 64
Reasoning 6
ARC-AGI-1public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 99% #2 of 61+1 versions & slices 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 Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 97.1% #6 of 63+1 versions & slices semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 90.4% #6 of 66
ARC-AGI-3semi-private Measures interactive game solving through relative human action efficiency ARC 30.2% #4 of 18
Chess Puzzles Models choose the best next move from a novel chess position Epoch 43% #24 of 68
Math 7
AA Analyst Agent Data-analyst tasks: the model explores data with tools and reports findings AA 53.8% #5 of 43
FrontierMath Erdos Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 0% #6 of 13
FrontierMath Tier 4 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 73.2% #11 of 54
FrontierMath Tiers 1–3 (v2) Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 85.6% #12 of 69
MathArenaArXivMath · June 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 82.6% #9 of 24+2 versions & slices BrokenArXiv · June 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 90.7% #5 of 24ArXivLean · June 2026 Answer accuracy on the named mathematics competition under the recorded effort MathArena 32.6% #2 of 9
Science 5
Humanity's Last Exam Very hard expert questions across many fields, written to stump today’s models AA 54.9% #6 of 337
CritPt (physics) Research-level physics problems that need many careful reasoning steps AA 29.1% #12 of 324
Vals Science Index Scientific problem solving across the index’s component evaluations Vals 47.9% #6 of 18
SciCode Writing code for real scientific computing problems (physics, biology, math) AA 56.4% #23 of 140
Terminal-Bench Science0.1 Agents complete expert-authored research workflows across five scientific domains in a terminal AA 28.6% #8 of 33
Coding 7 Leads on 2
Terminal-Bench4.0 Agents use a terminal to complete executable coding, system administration and research tasks in the 4.0 suite 49% #9 of 132+1 versions & slices 2.1 Older, easier version of Terminal-Bench; Still widely reported AA 89.1% #4 of 156
DeepSWE1.1 Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition 73.6% #3 of 44
WebDev Arena Human pairwise preferences in the stated webdev vote pool Arena 1,689 #7 of 97+1 versions & slices full cohort Human pairwise preferences in the stated webdev vote pool Arena 1,689 #7 of 97
SWE-bench Pro (v2 full) Agents resolve repository issues under the network-locked v2 protocol; full and 51-task Hard results are separate Scale 99.4% #1 of 16
SWE-bench Pro (v2 hard) Agents resolve repository issues under the network-locked v2 protocol; full and 51-task Hard results are separate Scale 98% #1 of 16
Agents 8 Leads on 1
AutomationBench-AA Agents orchestrate SaaS workflows through APIs; objectives receive credit only when the task has no guardrail violation AA 56.6% #28 of 133
AA-Briefcase1.1 · Elo Agents produce professional deliverables; blind pairwise comparisons produce the source Elo rating AA 1,659 #5 of 140
EnterpriseOps-Gym-AA Agents complete stateful enterprise workflows in eight domains; final database state determines success AA 47.5% #5 of 43
GDPval-AA (work tasks)2.1 Real work tasks from many professions (reports, spreadsheets, analyses), graded against expert work AA 61.1 #7 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 48.7% #1 of 21
EBR Bench Agents learn to play Earthborne Rangers across repeated playthroughs Epoch 45.7% #7 of 24
Furniture Assembly Models inspect furniture assembly photos, identify incorrect builds and locate the mistaken step Epoch 60.8% #7 of 31
τ³-BankingAA Agents retrieve banking knowledge and execute tools to resolve customer-support workflows AA 42.1% #14 of 134
Multimodal 3
MMMU-Pro (vision) College-level questions that require understanding images: charts, diagrams, photos AA 84.7% #5 of 127
Arena Vision Human pairwise preferences in the stated vision vote pool Arena 1,320 #3 of 88
Chartography Expert chart reasoning over professional scientific, medical, financial and engineering charts Surge 27.3% #17 of 37
Writing 18 Leads on 1
Arena Textcreative writing Human pairwise preferences in the stated text vote pool Arena 1,471 #10 of 195+14 versions & slices overall Human pairwise preferences in the stated text vote pool Arena 1,490 #11 of 196Chinese Human pairwise preferences in the stated text vote pool Arena 1,573 #4 of 181English Human pairwise preferences in the stated text vote pool Arena 1,507 #5 of 188French Human pairwise preferences in the stated text vote pool Arena 1,508 #4 of 149German Human pairwise preferences in the stated text vote pool Arena 1,526 #1 of 154instruction following Human pairwise preferences in the stated text vote pool Arena 1,518 #4 of 188Japanese Human pairwise preferences in the stated text vote pool Arena 1,515 #2 of 138Korean Human pairwise preferences in the stated text vote pool Arena 1,521 #2 of 144non-English Human pairwise preferences in the stated text vote pool Arena 1,500 #4 of 188Polish Human pairwise preferences in the stated text vote pool Arena 1,520 #2 of 133Russian Human pairwise preferences in the stated text vote pool Arena 1,507 #6 of 186Spanish Human pairwise preferences in the stated text vote pool Arena 1,519 #2 of 155overall · full cohort Human pairwise preferences in the stated text vote pool Arena 1,508 #4 of 188creative writing · full cohort Human pairwise preferences in the stated text vote pool Arena 1,492 #6 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 86.3% #1 of 95
EQ-Bench Creative Writingv3 Creative Writing v3 · Elo: Judge-rated creative writing under the v3 prompt set and pairwise ranking EQ-Bench 2,133 #3 of 91
Lech Mazur Short-Story Judges compare stories written to ten required elements; the comparison score can be negative Lech 3.7 #2 of 44
Health & law 5 Leads on 2
MLCR-AA Models synthesize long medical records; the headline credits concise answers judged both accurate and complete AA 55.6% #6 of 64
Vals LegalBench Legal reasoning and legal-language understanding on LegalBench Vals 87% #6 of 89
Vals MedCode Medical coding accuracy on patient encounters Vals 63.6% #1 of 78
Vals MedScribe Accuracy of clinical notes produced from consultation transcripts Vals 91% #4 of 80
Vals Legal Research Bench Grounded legal research; a task passes only if all criteria pass Vals 55.3% #1 of 69
Documents 3 Leads on 1
AA-LCR (long context)1.1 Questions that need reading and connecting facts across very long documents (around 100K tokens) AA 79.3% #52 of 275
GDP.pdfAA all-pass Models reason over professional PDF documents; an attempt passes only when every atomic criterion passes 21.6% #22 of 133
Arena Document Human pairwise preferences in the stated document vote pool Arena 1,516 #1 of 33
Legacy · saturated or no longer reported 9
GPQA Diamond Graduate-level biology, chemistry and physics questions that can’t be solved by a quick web search 93.2% #11 of 315+1 versions & slices Epoch Models answer graduate-level science multiple-choice questions Epoch 93.9% #11 of 133
OTIS Mock AIME 20242025 Models solve the stated OTIS mock AIME mathematics problems Epoch 98.9% #15 of 130
SWE-rebenchall · 2026-05-15 to 2026-07-01 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 63.4% #3 of 6+5 versions & slices Go · 2026-05-15 to 2026-07-01 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 73.3% #2 of 6Java · 2026-05-15 to 2026-07-01 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 48.6% #5 of 6Python · 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 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 61.6% #4 of 6TypeScript · 2026-05-15 to 2026-07-01 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 78.3% #1 of 6
No benchmark matches
CheaperGPT-6.1 Solmax+9%-88%$0.72Remove unsupported parameters+5
OpenKimi K3max-16%-66%$2.00Sampling parameters are fixed+3
GLM 5.3maxOpen-20%-66%$2.01No image input+4
DeepSeek V4 Pro 0813maxOpen-25%-88%$0.67No image input+5