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 13.1 #166 of 337
Knowledge 5
AA OmniscienceAccuracy AA Omniscience · Accuracy: Measures correct answers on the AA Omniscience factual knowledge test AA 26% #103 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 75.3% #145 of 321
AA Omniscience Index AA Omniscience Index: Scores factual knowledge while penalizing incorrect answers to encourage admitting uncertainty AA -29.8 #150 of 321
IFBench (instructions) IFBench (instructions): Checks whether the model follows precise formatting and content instructions AA 50.3% #115 of 248
SimpleQA Verifiedv1 SimpleQA Verified v1: Accuracy on short factual questions with verified answers, answered without web access 28.1% #61 of 83
Math 7
FrontierMath FrontierMath: Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 4.8% #31 of 40
FrontierMath Tier4 FrontierMath Tier 4: Models solve expert-written advanced mathematics problems on the named tier and edition Epoch 4.2% #16 of 33
MathArenaAIME 2025 MathArena · aime · AIME 2025: Answer accuracy on the named mathematics competition under the recorded effort MathArena 70.8% #24 of 30+4 versions & slices BRUMO 2025 MathArena · brumo · BRUMO 2025: Answer accuracy on the named mathematics competition under the recorded effort MathArena 83.3% #22 of 24CMIMC 2025 MathArena · cmimc · CMIMC 2025: Answer accuracy on the named mathematics competition under the recorded effort MathArena 54.4% #22 of 22HMMT February 2025 MathArena · hmmt · HMMT Feb 2025: Answer accuracy on the named mathematics competition under the recorded effort MathArena 64.2% #22 of 30SMT 2025 MathArena · smt · SMT 2025: Answer accuracy on the named mathematics competition under the recorded effort MathArena 75.5% #23 of 24
Science 2
Humanity's Last Exam Humanity's Last Exam: Very hard expert questions across many fields, written to stump today’s models AA 12.1% #160 of 337
CritPt (physics) CritPt (physics): Research-level physics problems that need many careful reasoning steps AA 1.1% #119 of 324
Coding 1
Terminal-Bench Hard Terminal-Bench Hard (version unstated): Agents solve difficult software, system-administration and data-processing tasks in a terminal AA 13.6% #114 of 242
Multimodal 2
MMMU-Pro (vision) MMMU-Pro (vision): College-level questions that require understanding images: charts, diagrams, photos AA 69.1% #75 of 127
Arena Vision Arena Vision · overall: Human pairwise preferences in the stated vision vote pool Arena 1,235 #53 of 88
Writing 15
Arena Textcreative writing Arena Text · creative writing: Human pairwise preferences in the stated text vote pool Arena 1,394 #73 of 195+14 versions & slices overall Arena Text · overall: Human pairwise preferences in the stated text vote pool Arena 1,409 #91 of 196Chinese Arena Text · chinese: Human pairwise preferences in the stated text vote pool Arena 1,450 #79 of 181English Arena Text · english: Human pairwise preferences in the stated text vote pool Arena 1,418 #85 of 188French Arena Text · french: Human pairwise preferences in the stated text vote pool Arena 1,432 #74 of 149German Arena Text · german: Human pairwise preferences in the stated text vote pool Arena 1,417 #61 of 154instruction following Arena Text · instruction following: Human pairwise preferences in the stated text vote pool Arena 1,405 #77 of 188Japanese Arena Text · japanese: Human pairwise preferences in the stated text vote pool Arena 1,396 #47 of 138Korean Arena Text · korean: Human pairwise preferences in the stated text vote pool Arena 1,385 #51 of 144non-English Arena Text · non english: Human pairwise preferences in the stated text vote pool Arena 1,409 #70 of 188Polish Arena Text · polish: Human pairwise preferences in the stated text vote pool Arena 1,413 #60 of 133Russian Arena Text · russian: Human pairwise preferences in the stated text vote pool Arena 1,415 #69 of 186Spanish Arena Text · spanish: Human pairwise preferences in the stated text vote pool Arena 1,421 #70 of 155overall · full cohort Arena Text · overall · snapshot 2026-10-15 · native board settings: Human pairwise preferences in the stated text vote pool Arena 1,417 #78 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 1,400 #63 of 187
Health & law 3
MLCR-AA MLCR-AA: Models synthesize long medical records; the headline credits concise answers judged both accurate and complete AA 8.9% #44 of 64
Vals MedCode Vals MedCode: Medical coding accuracy on patient encounters Vals 40.4% #51 of 78
Vals MedScribe Vals MedScribe: Accuracy of clinical notes produced from consultation transcripts Vals 83% #41 of 80
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 65.3% #140 of 275
Other 1
AA Speech to textRecorded audio word error rate AA Speech-to-Text · Non-streaming WER (version unstated): Measures transcription errors as a share of reference words in the non-streaming test AA 5.1% #43 of 55
Legacy · saturated or no longer reported 12
τ²-benchAA τ²-Bench: Tests service agents that use tools while coordinating with a simulated user AA 31.6% #146 of 245
AIME2025 · AA archived AIME 2025 · AA archived: AA evaluates the 30 integer-answer problems from the 2025 AIME mathematics competition AA 73.3% #61 of 140
LiveCodeBenchAA archived LiveCodeBench · AA archived: AA evaluates solutions to newly collected competitive-programming problems AA 69.5% #46 of 153
GPQA Diamond GPQA Diamond: Graduate-level biology, chemistry and physics questions that can’t be solved by a quick web search 79% #121 of 315
BFCLv4 BFCL v4: Tests function calling, multi-turn interactions, search and memory in the v4 suite Berkeley 56.2% #6 of 39+1 versions & slices v4 · prompt mode BFCL v4 · BFCL v4 source function-call format · historical run: Tests function calling, multi-turn interactions, search and memory in the v4 suite Berkeley 50.9% #1 of 16
SWE-rebenchall · 2025-07-01 to 2025-11-01 SWE-rebench · all · 2025-07-01 to 2025-11-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 19.9% #2 of 2+5 versions & slices Go · 2025-07-01 to 2025-11-01 SWE-rebench · go · 2025-07-01 to 2025-11-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 2Java · 2025-07-01 to 2025-11-01 SWE-rebench · java · 2025-07-01 to 2025-11-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 2Python · 2025-07-01 to 2025-11-01 SWE-rebench · python · 2025-07-01 to 2025-11-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 19.9% #2 of 2Rust · 2025-07-01 to 2025-11-01 SWE-rebench · rust · 2025-07-01 to 2025-11-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 2TypeScript · 2025-07-01 to 2025-11-01 SWE-rebench · typescript · 2025-07-01 to 2025-11-01: Repository issue resolution over the exact fresh pull-request window, under the source agent version Nebius 0% #1 of 2
No benchmark matches
CheaperGPT OSS 120BhighOpen+26%-93%$0.092Context: 1M → 131K+1
OpenDeepSeek V3.2 Specialethinking+29%——Context: 1M → 128K+1
CheaperMiniMax M2thinkingOpen+19%-38%$0.30 / $1.20Context: 1M → 205K+1
Nemotron 3 Nano 30B A3BthinkingOpen+7%-88%$0.017Context: 1M → 131K+1
GLM 4.7thinkingOpen+29%+18%$0.60 / $2.20Context: 1M → 203K+1
Kimi K2 ThinkingthinkingOpen+23%same$0.47 / $2Context: 1M → 256K+1