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 30.1 #59 of 339
Knowledge 7
AA OmniscienceAccuracy Measures correct answers on the AA Omniscience factual knowledge test AA 40.9% #46 of 323+1 versions & slices Hallucination Rate Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test AA 48.4% #83 of 323
AA Omniscience Index Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA 12.2 #37 of 323
IFBench (instructions) Checks whether the model follows precise formatting and content instructions AA 56.6% #99 of 248
EQ-Bench3 Judge-rated responses to social and emotionally nuanced scenarios, scored through the source pairwise ranking EQ-Bench 1,710 #5 of 53
SimpleQA Verifiedv1 Accuracy on short factual questions with verified answers, answered without web access 32.8% #55 of 84
Mystery Game Puzzles Models choose the best move in puzzle positions from an undisclosed game Epoch 16% #50 of 65
Reasoning 5
ARC-AGI-1public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 95.8% #23 of 64+1 versions & slices semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 86% #36 of 67
ARC-AGI-2public evaluation Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 62.4% #25 of 66+1 versions & slices semi-private Models infer transformations from examples and solve unseen grid puzzles; the evaluation split is explicit ARC 58.3% #32 of 69
Chess Puzzles Models choose the best next move from a novel chess position Epoch 23% #46 of 69
Math 1
AA Analyst Agent Data-analyst tasks: the model explores data with tools and reports findings AA 20% #30 of 43
Science 3
Humanity's Last Exam Very hard expert questions across many fields, written to stump today’s models AA 33.6% #72 of 339
CritPt (physics) Research-level physics problems that need many careful reasoning steps AA 3.1% #94 of 326
SciCode Writing code for real scientific computing problems (physics, biology, math) AA 50.1% #52 of 142
Coding 9
Terminal-Bench4.0 Agents use a terminal to complete executable coding, system administration and research tasks in the 4.0 suite 3% #48 of 134+1 versions & slices 2.1 Older, easier version of Terminal-Bench; Still widely reported AA 71.2% #34 of 156
DeepSWE1.1 Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition 29.9% #33 of 44+1 versions & slices 1 Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition Datacurve 31.8% #6 of 20
ITBench SRE IT incident tasks: diagnose and fix broken systems like a site-reliability engineer AA 39.8% #19 of 37
WebDev Arena Human pairwise preferences in the stated webdev vote pool Arena 1,523 #42 of 97+2 versions & slices October 23, 2026 Human pairwise preferences in the stated webdev vote pool Arena 1,523 #43 of 98October 19, 2026 Human pairwise preferences in the stated webdev vote pool Arena 1,523 #42 of 97
Terminal-Bench Hard Agents solve difficult software, system-administration and data-processing tasks in a terminal AA 53% #9 of 242
Agents 7
AutomationBench-AA Agents orchestrate SaaS workflows through APIs; objectives receive credit only when the task has no guardrail violation AA 20.1% #63 of 135
AA-Briefcase1.1 · Elo Agents produce professional deliverables; blind pairwise comparisons produce the source Elo rating AA 1,062 #53 of 142
APEX-Agents Agents complete long-horizon professional-services tasks across realistic applications AA 28% #14 of 29
GDPval-AA (work tasks)2.1 Real work tasks from many professions (reports, spreadsheets, analyses), graded against expert work AA 1,233 #49 of 177
MCP-Atlas Public MCPAtlas Public: MCPAtlas Public as reported in this launch evaluation; the post is the authority for the recorded task and grading scope 72.8% #8 of 16
MCP-Atlasfull 1000 Tool orchestration across MCP servers on the stated task split Scale 69.5% #8 of 16
τ³-BankingAA Agents retrieve banking knowledge and execute tools to resolve customer-support workflows AA 34.4% #28 of 134
Multimodal 2
MMMU-Pro (vision) College-level questions that require understanding images: charts, diagrams, photos AA 73.3% #63 of 128
Arena Vision Human pairwise preferences in the stated vision vote pool Arena 1,283 #22 of 88
Writing 19
Arena Textcreative writing · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,435 #36 of 197+16 versions & slices creative writing Human pairwise preferences in the stated text vote pool Arena 1,449 #27 of 195overall Human pairwise preferences in the stated text vote pool Arena 1,472 #31 of 196Chinese Human pairwise preferences in the stated text vote pool Arena 1,491 #49 of 198English Human pairwise preferences in the stated text vote pool Arena 1,472 #26 of 205French Human pairwise preferences in the stated text vote pool Arena 1,465 #39 of 164German Human pairwise preferences in the stated text vote pool Arena 1,428 #54 of 167instruction following Human pairwise preferences in the stated text vote pool Arena 1,476 #20 of 205Japanese Human pairwise preferences in the stated text vote pool Arena 1,420 #36 of 152Korean Human pairwise preferences in the stated text vote pool Arena 1,410 #37 of 156non-English Human pairwise preferences in the stated text vote pool Arena 1,440 #35 of 205Polish Human pairwise preferences in the stated text vote pool Arena 1,442 #36 of 142Russian Human pairwise preferences in the stated text vote pool Arena 1,440 #45 of 203Spanish Human pairwise preferences in the stated text vote pool Arena 1,464 #26 of 168overall · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,458 #30 of 188creative writing · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,435 #37 of 187overall · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,458 #30 of 198
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 79.9% #16 of 96
EQ-Bench Creative Writingv3 Creative Writing v3 · Elo: Judge-rated creative writing under the v3 prompt set and pairwise ranking EQ-Bench 1,811 #24 of 94
Health & law 3
MLCR-AA Models synthesize long medical records; the headline credits concise answers judged both accurate and complete AA 7.8% #66 of 103
Vals LegalBench Legal reasoning and legal-language understanding on LegalBench Vals 82.1% #54 of 89
Vals Legal Research Bench Grounded legal research; a task passes only if all criteria pass Vals 38.5% #29 of 73
Documents 3
AA-LCR (long context)1.1 Questions that need reading and connecting facts across very long documents (around 100K tokens) AA 80% #44 of 317
GDP.pdfAA all-pass Models reason over professional PDF documents; an attempt passes only when every atomic criterion passes 15.8% #37 of 135
Arena Document Human pairwise preferences in the stated document vote pool Arena 1,482 #8 of 33
Legacy · saturated or no longer reported 11
GPQA Diamond Graduate-level biology, chemistry and physics questions that can’t be solved by a quick web search 87.5% #52 of 315+1 versions & slices Epoch Models answer graduate-level science multiple-choice questions Epoch 78.8% #71 of 134
OTIS Mock AIME 20242025 Models solve the stated OTIS mock AIME mathematics problems Epoch 71.1% #74 of 131
SWE-bench VerifiedEpoch Swe Bench Verified: Agents modify real repositories to resolve the stated Verified issues Epoch 75.2% #11 of 24
SWE-rebenchall · February 1, 2026 to May 15, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 54.5% #3 of 4+5 versions & slices Go · February 1, 2026 to May 15, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 4Java · February 1, 2026 to May 15, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 4Python · February 1, 2026 to May 15, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 54.5% #3 of 4Rust · February 1, 2026 to May 15, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 4TypeScript · February 1, 2026 to May 15, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 4
τ²-benchAA Tests service agents that use tools while coordinating with a simulated user AA 75.7% #88 of 245
No benchmark matches
BetterGPT-6 Lunahigh+10%-99%$0.029Function calling only with none · Chat Completions+3
OpenMiMo v2.6 Prothinking+54%-95%$0.13Pass back reasoning_content+3
CheaperGemini 4 Argonhigh+75%-35%*$1.62Synchronous output stops at 65,536+2
DeepSeek V4.1 Flash 1017maxOpen+50%-89%$0.26Pass back reasoning_content · Chat Completions+4
GLM 5.3maxOpen+49%-19%$2.01No image input+4
Step 5 PreviewthinkingOpen+46%-59%$1.03web_search not available · Chat Completions+2
Kimi K3maxOpen+45%-20%$2.00Sampling parameters are fixed+3