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 29.1 #63 of 339
Knowledge 6
AA OmniscienceAccuracy Measures correct answers on the AA Omniscience factual knowledge test AA 46.6% #33 of 323+1 versions & slices Hallucination Rate Measures how often attempted answers are incorrect on the AA Omniscience factual knowledge test AA 61% #110 of 323
AA Omniscience Index Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA 14 #34 of 323
IFBench (instructions) Checks whether the model follows precise formatting and content instructions AA 58% #90 of 248
EQ-Bench3 Judge-rated responses to social and emotionally nuanced scenarios, scored through the source pairwise ranking EQ-Bench 1,522 #19 of 53
SimpleQA Verifiedv1 Accuracy on short factual questions with verified answers, answered without web access 39% #44 of 84
Reasoning 1
Chess Puzzles Models choose the best next move from a novel chess position Epoch 5% #66 of 69
Math 2
FrontierMath Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 20.7% #21 of 40
FrontierMath Tier4 Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 4.2% #16 of 33
Science 2
Humanity's Last Exam Very hard expert questions across many fields, written to stump today’s models AA 30.1% #81 of 339
CritPt (physics) Research-level physics problems that need many careful reasoning steps AA 4.6% #83 of 326
Coding 5
WebDev Arena Human pairwise preferences in the stated webdev vote pool Arena 1,494 #47 of 97+2 versions & slices October 23, 2026 Human pairwise preferences in the stated webdev vote pool Arena 1,494 #48 of 98October 19, 2026 Human pairwise preferences in the stated webdev vote pool Arena 1,494 #47 of 97
SWE-bench Pro (private) Agents resolve long-horizon professional repository tasks; public and private splits are separate Scale 23.4% #7 of 9
Terminal-Bench Hard Agents solve difficult software, system-administration and data-processing tasks in a terminal AA 47% #16 of 242
Agents 3
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 73.4% #7 of 16
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 24.7% #18 of 21
MCP-Atlasfull 1000 Tool orchestration across MCP servers on the stated task split Scale 69.8% #7 of 16
Multimodal 2
MMMU-Pro (vision) College-level questions that require understanding images: charts, diagrams, photos AA 74% #58 of 128
MMMUvalidation Image-grounded university-level questions across 30 disciplines; validation and test sets remain separate MMMU 80.7% #3 of 41
Writing 19
Arena Textcreative writing · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,445 #27 of 197+16 versions & slices creative writing Human pairwise preferences in the stated text vote pool Arena 1,469 #12 of 195overall Human pairwise preferences in the stated text vote pool Arena 1,474 #27 of 196Chinese Human pairwise preferences in the stated text vote pool Arena 1,470 #64 of 198English Human pairwise preferences in the stated text vote pool Arena 1,461 #32 of 205French Human pairwise preferences in the stated text vote pool Arena 1,471 #35 of 164German Human pairwise preferences in the stated text vote pool Arena 1,450 #38 of 167instruction following Human pairwise preferences in the stated text vote pool Arena 1,478 #18 of 205Japanese Human pairwise preferences in the stated text vote pool Arena 1,417 #38 of 152Korean Human pairwise preferences in the stated text vote pool Arena 1,424 #30 of 156non-English Human pairwise preferences in the stated text vote pool Arena 1,438 #38 of 205Polish Human pairwise preferences in the stated text vote pool Arena 1,439 #40 of 142Russian Human pairwise preferences in the stated text vote pool Arena 1,447 #39 of 203Spanish Human pairwise preferences in the stated text vote pool Arena 1,457 #32 of 168overall · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,451 #37 of 188creative writing · October 15, 2026 Human pairwise preferences in the stated text vote pool Arena 1,443 #27 of 187overall · October 22, 2026 Human pairwise preferences in the stated text vote pool Arena 1,451 #37 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 73.1% #32 of 96
EQ-Bench Creative Writingv3 Creative Writing v3 · Elo: Judge-rated creative writing under the v3 prompt set and pairwise ranking EQ-Bench 1,687 #34 of 94
Health & law 3
Vals LegalBench Legal reasoning and legal-language understanding on LegalBench Vals 84.6% #27 of 89
Vals MedCode Medical coding accuracy on patient encounters Vals 49.2% #21 of 78
Vals MedScribe Accuracy of clinical notes produced from consultation transcripts Vals 85.3% #26 of 80
Documents 2
AA-LCR (long context)1.1 Questions that need reading and connecting facts across very long documents (around 100K tokens) AA 77.3% #78 of 317
Arena Document Human pairwise preferences in the stated document vote pool Arena 1,462 #16 of 33
Legacy · saturated or no longer reported 20
SWE-bench Pro (public) Agents resolve long-horizon professional repository tasks; public and private splits are separate 45.9% #6 of 19
AIME2025 · AA archived AA evaluates the 30 integer-answer problems from the 2025 AIME mathematics competition AA 91.3% #11 of 140
LiveCodeBenchAA archived AA evaluates solutions to newly collected competitive-programming problems AA 87.1% #6 of 153
GPQA Diamond Graduate-level biology, chemistry and physics questions that can’t be solved by a quick web search 86.6% #64 of 315+1 versions & slices Epoch Models answer graduate-level science multiple-choice questions Epoch 80.7% #69 of 134
BFCLv4 Tests function calling, multi-turn interactions, search and memory in the v4 suite Berkeley 77.5% #1 of 39+1 versions & slices v4 · prompt mode Tests function calling, multi-turn interactions, search and memory in the v4 suite Berkeley 33.5% #9 of 16
τ²-benchairline · 1.0.1 τ-bench official · 2-airline-1.0.1: Customer-service agents converse with simulated users, retrieve domain knowledge and change state through tools Sierra 84% #1 of 6+4 versions & slices overall · 1.0.1 τ-bench official · 2-overall-1.0.1: Customer-service agents converse with simulated users, retrieve domain knowledge and change state through tools Sierra 85.3% #2 of 6retail · 1.0.1 τ-bench official · 2-retail-1.0.1: Customer-service agents converse with simulated users, retrieve domain knowledge and change state through tools Sierra 79.6% #3 of 6telecom · 1.0.1 τ-bench official · 2-telecom-1.0.1: Customer-service agents converse with simulated users, retrieve domain knowledge and change state through tools Sierra 92.3% #2 of 6AA Tests service agents that use tools while coordinating with a simulated user AA 89.5% #44 of 245
OTIS Mock AIME 20242025 Models solve the stated OTIS mock AIME mathematics problems Epoch 48.1% #95 of 131
SWE-bench VerifiedEpoch Swe Bench Verified: Agents modify real repositories to resolve the stated Verified issues Epoch 76.7% #6 of 24
SWE-rebenchall · October 1, 2025 to February 1, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 53.1% #1 of 1+5 versions & slices Go · October 1, 2025 to February 1, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 1Java · October 1, 2025 to February 1, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 1Python · October 1, 2025 to February 1, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 53.1% #1 of 1Rust · October 1, 2025 to February 1, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 1TypeScript · October 1, 2025 to February 1, 2026 Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 1
No benchmark matches
BetterGPT-6 Lunahigh+13%-98%$0.029Function calling only with none · Chat Completions+3
OpenMiMo v2.6 Prothinking+59%-95%$0.13Pass back reasoning_content+3
CheaperGemini 4 Argonhigh+81%-60%*$1.62Synchronous output stops at 65,536+2
Muse Wondermax+80%-20%$8.63Only auto tool_choice is supported+5
DeepSeek V4.1 Flash 1017maxOpen+55%-95%$0.26Pass back reasoning_content · Chat Completions+4
GLM 5.3maxOpen+54%-79%$2.01No image input+4
Step 5 PreviewthinkingOpen+50%-86%$1.03web_search not available · Chat Completions+2
Kimi K3maxOpen+50%-40%$2.00Sampling parameters are fixed+3