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 26 #79 of 339
Knowledge 4
AA OmniscienceAccuracy Measures correct answers on the AA Omniscience factual knowledge test AA 22.4% #136 of 323+1 versions & slices Hallucination Rate Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test AA 24.7% #18 of 323
AA Omniscience Index Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA 3.3 #59 of 323
IFBench (instructions) Checks whether the model follows precise formatting and content instructions AA 79.9% #6 of 248
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 35.7% #61 of 339
CritPt (physics) Research-level physics problems that need many careful reasoning steps AA 4% #89 of 326
SciCode Writing code for real scientific computing problems (physics, biology, math) AA 50.6% #50 of 142
Coding 8
Terminal-Bench4.0 Agents use a terminal to complete executable coding, system administration and research tasks in the 4.0 suite 0% #77 of 134+1 versions & slices 2.1 Older, easier version of Terminal-Bench; Still widely reported AA 65.2% #43 of 156
ITBench SRE IT incident tasks: diagnose and fix broken systems like a site-reliability engineer AA 38.2% #20 of 37
WebDev Arena Human pairwise preferences in the stated webdev vote pool Arena 1,480 #50 of 97+2 versions & slices October 23, 2026 Human pairwise preferences in the stated webdev vote pool Arena 1,481 #51 of 98October 19, 2026 Human pairwise preferences in the stated webdev vote pool Arena 1,480 #50 of 97
DeepSWE1 Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition Datacurve 19.5% #11 of 20
Terminal-Bench Hard Agents solve difficult software, system-administration and data-processing tasks in a terminal AA 43.2% #25 of 242
Agents 5
AutomationBench-AA Agents orchestrate SaaS workflows through APIs; objectives receive credit only when the task has no guardrail violation AA 13.7% #73 of 135
AA-Briefcase1.1 · Elo Agents produce professional deliverables; blind pairwise comparisons produce the source Elo rating AA 883 #69 of 142
APEX-Agents Agents complete long-horizon professional-services tasks across realistic applications AA 2.4% #27 of 29
GDPval-AA (work tasks)2.1 Real work tasks from many professions (reports, spreadsheets, analyses), graded against expert work AA 1,121 #59 of 177
τ³-BankingAA Agents retrieve banking knowledge and execute tools to resolve customer-support workflows AA 9.9% #90 of 134
Writing 20
Arena Textcreative writing · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,438 #34 of 197+16 versions & slices creative writing Human pairwise preferences in the stated text vote pool Arena 1,434 #42 of 195overall Human pairwise preferences in the stated text vote pool Arena 1,467 #32 of 196Chinese Human pairwise preferences in the stated text vote pool Arena 1,506 #35 of 198English Human pairwise preferences in the stated text vote pool Arena 1,477 #21 of 205French Human pairwise preferences in the stated text vote pool Arena 1,487 #23 of 164German Human pairwise preferences in the stated text vote pool Arena 1,459 #27 of 167instruction following Human pairwise preferences in the stated text vote pool Arena 1,475 #21 of 205Japanese Human pairwise preferences in the stated text vote pool Arena 1,410 #44 of 152Korean Human pairwise preferences in the stated text vote pool Arena 1,436 #21 of 156non-English Human pairwise preferences in the stated text vote pool Arena 1,448 #31 of 205Polish Human pairwise preferences in the stated text vote pool Arena 1,463 #20 of 142Russian Human pairwise preferences in the stated text vote pool Arena 1,449 #38 of 203Spanish Human pairwise preferences in the stated text vote pool Arena 1,468 #24 of 168overall · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,465 #27 of 188creative writing · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,438 #35 of 187overall · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,464 #27 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 73.7% #30 of 96
EQ-Bench Creative Writingv3 Creative Writing v3 · Elo: Judge-rated creative writing under the v3 prompt set and pairwise ranking EQ-Bench 1,493 #51 of 94
Lech Mazur Short-Story Judges compare stories written to ten required elements; the comparison score can be negative Lech -0.7 #28 of 45
Health & law 5
MLCR-AA Models synthesize long medical records; the headline credits concise answers judged both accurate and complete AA 5.6% #76 of 103
Vals LegalBench Legal reasoning and legal-language understanding on LegalBench Vals 77.1% #73 of 89
Vals MedCode Medical coding accuracy on patient encounters Vals 32.5% #67 of 78
Vals MedScribe Accuracy of clinical notes produced from consultation transcripts Vals 83.7% #36 of 80
Vals Legal Research Bench Grounded legal research; a task passes only if all criteria pass Vals 15.9% #55 of 73
Documents 2
GDP.pdfAA all-pass Models reason over professional PDF documents; an attempt passes only when every atomic criterion passes 4% #93 of 135
AA-LCR (long context)1.1 Questions that need reading and connecting facts across very long documents (around 100K tokens) AA 79.7% #50 of 317
Legacy · saturated or no longer reported 8
GPQA Diamond Graduate-level biology, chemistry and physics questions that can’t be solved by a quick web search 86.6% #64 of 315
SWE-rebenchall · March 1, 2026 to July 1, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 44.4% #3 of 6+5 versions & slices Go · March 1, 2026 to July 1, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 56.2% #2 of 6Java · March 1, 2026 to July 1, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 42.9% #3 of 6Python · March 1, 2026 to July 1, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 42.6% #3 of 6Rust · March 1, 2026 to July 1, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 44% #3 of 6TypeScript · March 1, 2026 to July 1, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 45.8% #3 of 6
τ²-benchAA Tests service agents that use tools while coordinating with a simulated user AA 94.2% #23 of 245
No benchmark matches
CheaperGemma 4 31BunstatedOpen-1.2-71%$0.10 / $0.34Context: 1M → 256K
OpenGLM 5.3max+3.7+295%$2.01Reasoning cannot be disabled+3
CheaperGPT OSS 120BunstatedOpen-2.5-89%$0.03 / $0.15Context: 1M → 131K
Claude Opus 5.5high+4.4+1,371%$1.82No forced tool use+5
DeepSeek V4 Pro 0813highOpen+1.2+264%$1.32 / $3.96Memory (4-bit): 614 GB → 990 GB+5
Kimi K2.6unstatedOpensame+215%$0.95 / $4Context: 1M → 256K+1