In one line：LiveBench 是一个抗污染的动态评测榜，看模型「现在」的实际水平。
LiveBench 是一个抗污染的动态评测榜，看模型「现在」的实际水平。
Official source
We host and mirror nothing — the official page is the source of truth.
Read the original (we index it, never rehost it)
https://github.com/LiveBench/LiveBenchLiveBenchYou are leaving AIWorksWell for LiveBench. That site is not under our control; its content, privacy and security are its own responsibility. Please judge for yourself.Bugs in the software itself go to the author's own official channel — that is where they actually receive them. We pass things on; we do not answer for the author.
LiveBench 是一个持续更新题库的模型评测榜单，因为题目会换，被训练数据污染的可能更低。来源：https://livebench.ai/https://livebench.ai/
选模型前对照 LiveBench 的分项得分，别只看一个总分——分项才说明该模型擅长什么。来源：https://livebench.ai/https://livebench.ai/
Mentioned from：https://livebench.ai/https://livebench.ai/ · 原作者 LiveBench（Apache-2.0）。
Summary for AI
一个抗污染的动态评测基准，专门回答「模型现在是什么水平」：题目定期更新并带明确答案，模型很难靠「见过原题」刷分。数据与跑分口径都在官方仓库公开，结果可自行复核。
A self-contained answer paragraph — this is the part AI search quotes. · Page reviewed 2026-10-06
差别在「动态」与「抗污染」——题目会换，降低训练数据里见过原题带来的虚高。
同一期同一口径下可以横向比；跨期比较意义有限，因为题目已经换过了。
We store, mirror and repackage nothing. Every install path points to the author’s own official page.
Nothing here has been reviewed by an app store. Judge the source and licence yourself; you install at your own risk.