llm.ing

Benchmarks

Every benchmark we aggregate, what it measures, and where its numbers come from.

agentic

BenchmarkModelsUnitRun byNotes
AA Agentic Index87indexArtificial Analysis

coding

BenchmarkModelsUnitRun byNotes
AA Coding Index92indexArtificial Analysis

intelligence

BenchmarkModelsUnitRun byNotes
AA Intelligence Index125indexArtificial AnalysisComposite of independently run evals by Artificial Analysis.

preference

BenchmarkModelsUnitRun byNotes
LMArena Text72eloLMArenaOverall text category; style effects not controlled in this config.
LMArena WebDev57eloLMArenaHead-to-head web app building votes.
LMArena Vision53eloLMArenaImage-understanding battles.
Design Arena — 25 categories (crowd-voted design/code battles)
Design Arena — website74eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — codecategories72eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — dataviz72eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — uicomponent71eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — gamedev70eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — 3d69eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — svg54eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — asciiart44eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — webapps33eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — fullstack32eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — mobileapps30eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — godotgamedev29eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — androidnative29eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — python-pptxslides18eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — agenticgamedev18eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — htmlslides18eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — agentichtmlslides10eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — agenticslides(html)10eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — agenticslides10eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — agenticslides(python-pptx)10eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — pptxslides9eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — graphicdesign3eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — image3eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — logo3eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — imageediting1eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.

speed

BenchmarkModelsUnitRun byNotes
Median output speed48tokens_per_sArtificial Analysis
Median time to first token48secondsArtificial Analysis