Benchmark

Artificial Analysis

Artificial Analysis benchmark evaluates AI models across quality, speed, and pricing dimensions, providing a composite assessment of model capabilities…

Modality
text
Categories
general
Openness
unknown
Source
llm_stats
Reported scores
7

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
Gemini 3.7 FlashGoogle0.562026-08-13evidence
GPT-5.6 LunaOpenAI0.512026-07-09evidence
GPT-5.6 SolOpenAI0.592026-07-09evidence
GPT-5.6 TerraOpenAI0.552026-07-09evidence
Grok 4.5xAI0.542026-07-16evidence
Inkling-SmallThinking Machines Lab0.42026-07-30evidence
MiniMax M2.7MiniMax0.52026-03-18evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.