llm.ing

Benchmarks

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

agentic

BenchmarkModelsUnitRun byNotes
AA Agentic Index104indexArtificial Analysis

coding

BenchmarkModelsUnitRun byNotes
AA Coding Index109indexArtificial Analysis

intelligence

BenchmarkModelsUnitRun byNotes
AA Intelligence Index142indexArtificial AnalysisComposite of independently run evals by Artificial Analysis.

preference

BenchmarkModelsUnitRun byNotes
LMArena Text127eloLMArenaOverall text category; style effects not controlled in this config.
LMArena WebDev71eloLMArenaHead-to-head web app building votes.
LMArena Vision68eloLMArenaImage-understanding battles.
Design Arena — 25 categories (crowd-voted design/code battles)
Design Arena — website84eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — codecategories82eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — dataviz82eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — uicomponent82eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — gamedev82eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — 3d79eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — svg65eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — asciiart54eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — fullstack43eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — mobileapps43eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — webapps42eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — androidnative36eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — godotgamedev31eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — python-pptxslides27eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — agenticgamedev25eloDesign ArenaHead-to-head human votes on generated designs/code, mirrored via OpenRouter.
Design Arena — htmlslides24eloDesign 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 speed54tokens_per_sArtificial Analysis
Median time to first token54secondsArtificial Analysis