AI benchmarks: what each one measures

9 of 85 benchmarks

Benchmark	Domain	Introduced	Paper	Scores
LMArena Text Arena (Chatbot Arena)Chat: people ask anything and vote for the better of two anonymous answers.Arenas · 2023LMArena (from LMSYS, UC Berkeley)	Arenas	May 20233 years ago	2403.04132	84
LMArena WebDev ArenaBuild a web app from a prompt; people vote for the better of two.ArenasLMArena	Arenas		·	84
LMArena Vision ArenaChat about images; people vote for the better answer.ArenasLMArena	Arenas		·	85
LMArena Document ArenaAnswer questions about uploaded documents and PDFs; people vote.ArenasLMArena	Arenas		·	40
LMArena Search ArenaAnswer with web search grounding; people vote for the better answer.ArenasLMArena	Arenas		·	40
LMArena Text-to-ImageGenerate an image from a prompt; people vote for the better of two.ArenasLMArena	Arenas		·	71
LMArena Image EditEdit an image from an instruction; people vote for the better edit.ArenasLMArena	Arenas		·	51
LMArena Text-to-VideoGenerate a video from a prompt; people vote for the better of two.ArenasLMArena	Arenas		·	46
LMArena Image-to-VideoAnimate an image into a video; people vote for the better of two.ArenasLMArena	Arenas		·	45

Scores counts the models with a captured score on the boards that publish this benchmark. A dot means we capture no board for it yet.

Sources: each benchmark's paper (arXiv) and its official site or leaderboard. Scores are the boards captured here every day, exactly as published.

AI benchmarks: what is being measured