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 19.3 #124 of 337
Knowledge 4
AA OmniscienceAccuracy AA Omniscience · Accuracy: Measures correct answers on the AA Omniscience factual knowledge test AA 20.1% #154 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 85.4% #206 of 321
AA Omniscience Index AA Omniscience Index: Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA -48.1 #200 of 321
IFBench (instructions) IFBench (instructions): Checks whether the model follows precise formatting and content instructions AA 72.5% #36 of 248
Math 7
MathArenaAIME 2026 MathArena · AIME 2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 93.3% #19 of 24+6 versions & slices HMMT February 2026 MathArena · HMMT February 2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 81.8% #20 of 24Apex MathArena · apex · Apex: Answer accuracy on the named mathematics competition under the recorded effort MathArena 4.2% #21 of 34Apex Shortlist MathArena · apex · Apex Shortlist: Answer accuracy on the named mathematics competition under the recorded effort MathArena 44.7% #25 of 30ArXivMath · December 2025 MathArena · arxiv · 12/2025: Answer accuracy on the named mathematics competition under the recorded effort MathArena 39.7% #8 of 13ArXivMath · February 2026 MathArena · arxiv · 02/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 30.5% #17 of 20ArXivMath · January 2026 MathArena · arxiv · 01/2026: Answer accuracy on the named mathematics competition under the recorded effort MathArena 50% #15 of 18
Science 2
Humanity's Last Exam Humanity's Last Exam: Very hard expert questions across many fields, written to stump today’s models AA 21% #120 of 337
CritPt (physics) CritPt (physics): Research-level physics problems that need many careful reasoning steps AA 0.9% #130 of 324
Coding 4
WebDev Arena WebDev Arena: Human pairwise preferences in the stated webdev vote pool Arena 1,254 #90 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 1,254 #90 of 97
ITBench SRE ITBench SRE: IT incident tasks: diagnose and fix broken systems like a site-reliability engineer AA 21.5% #35 of 37
Terminal-Bench Hard Terminal-Bench Hard (version unstated): Agents solve difficult software, system-administration and data-processing tasks in a terminal AA 26.5% #68 of 242
Agents 2
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 #115 of 175
τ³-BankingAA τ³-Banking · AA: Agents retrieve banking knowledge and execute tools to resolve customer-support workflows AA 4.9% #120 of 134
Multimodal 1
MMMU-Pro (vision) MMMU-Pro (vision): College-level questions that require understanding images: charts, diagrams, photos AA 72.7% #67 of 127
Writing 16
Arena Textcreative writing Arena Text · creative writing: Human pairwise preferences in the stated text vote pool Arena 1,343 #105 of 195+14 versions & slices overall Arena Text · overall: Human pairwise preferences in the stated text vote pool Arena 1,394 #104 of 196Chinese Arena Text · chinese: Human pairwise preferences in the stated text vote pool Arena 1,457 #74 of 181English Arena Text · english: Human pairwise preferences in the stated text vote pool Arena 1,407 #93 of 188French Arena Text · french: Human pairwise preferences in the stated text vote pool Arena 1,412 #84 of 149German Arena Text · german: Human pairwise preferences in the stated text vote pool Arena 1,367 #88 of 154instruction following Arena Text · instruction following: Human pairwise preferences in the stated text vote pool Arena 1,379 #92 of 188Japanese Arena Text · japanese: Human pairwise preferences in the stated text vote pool Arena 1,326 #79 of 138Korean Arena Text · korean: Human pairwise preferences in the stated text vote pool Arena 1,354 #77 of 144non-English Arena Text · non english: Human pairwise preferences in the stated text vote pool Arena 1,378 #95 of 188Polish Arena Text · polish: Human pairwise preferences in the stated text vote pool Arena 1,386 #77 of 133Russian Arena Text · russian: Human pairwise preferences in the stated text vote pool Arena 1,377 #95 of 186Spanish Arena Text · spanish: Human pairwise preferences in the stated text vote pool Arena 1,391 #91 of 155overall · full cohort Arena Text · overall · snapshot 2026-10-15 · native board settings: Human pairwise preferences in the stated text vote pool Arena 1,395 #95 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 1,348 #93 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 44.5% #72 of 95
Documents 1
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 72% #108 of 275
Legacy · saturated or no longer reported 11
GPQA Diamond GPQA Diamond: Graduate-level biology, chemistry and physics questions that can’t be solved by a quick web search 84.5% #85 of 315+1 versions & slices Epoch GPQA Diamond · source setting 2: Models answer graduate-level science multiple-choice questions Epoch 83.5% #59 of 133
OTIS Mock AIME 20242025 OTIS Mock AIME 2024 2025: Models solve the stated OTIS mock AIME mathematics problems Epoch 70% #77 of 130
SWE-rebenchall · 2026-02-01 to 2026-07-01 SWE-rebench · all · 2026-02-01 to 2026-07-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 29.5% #1 of 1+5 versions & slices Go · 2026-02-01 to 2026-07-01 SWE-rebench · go · 2026-02-01 to 2026-07-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 18.1% #1 of 1Java · 2026-02-01 to 2026-07-01 SWE-rebench · java · 2026-02-01 to 2026-07-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 16.2% #1 of 1Python · 2026-02-01 to 2026-07-01 SWE-rebench · python · 2026-02-01 to 2026-07-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 42.6% #1 of 1Rust · 2026-02-01 to 2026-07-01 SWE-rebench · rust · 2026-02-01 to 2026-07-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 22.4% #1 of 1TypeScript · 2026-02-01 to 2026-07-01 SWE-rebench · typescript · 2026-02-01 to 2026-07-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 16.7% #1 of 1
τ²-benchAA τ²-Bench: Tests service agents that use tools while coordinating with a simulated user AA 89.2% #46 of 245
Terminal-Bench2.1 Terminal-Bench 2.1 · source setting 2: Older, easier version of Terminal-Bench; Still widely reported AA 40.8% #83 of 156
No benchmark matches
CheaperMiMo v2.6 ProthinkingOpen×2.4-21%$0.13Memory (4-bit): 22 GB → 615 GB+4
BetterGPT-6 Lunalow+11%-71%$0.005Function calling only with none · Chat Completions+3
CheaperDeepSeek V4.1 Flash 1017maxOpen×2.3-24%$0.26Memory (4-bit): 22 GB → 458 GB+5
CheaperClaude Haiku 5.5max×2.2-71%$0.21Remove sampling parameters+5
MiniMax M3.1 Flashthinking×2.2-62%$0.22Complete model response must be appended
GLM 5.3 FlashmaxOpen×2.2-65%$0.28Memory (4-bit): 22 GB → 193 GB+5