LiveBench B
AI benchmark · Knowledge
What is LiveBench?
A contamination-limited benchmark with frequently updated questions spanning math, coding, reasoning, language, instruction following, and data analysis.
Tier B
Established: 15 or more models scored, or curated RL directories rate it.
How much stands behind a tier: usage, who backs it, a confirmed line from its own site or paper, and a clear read on X. High with three of the four, medium with two, low otherwise.
- 43 models scored
- in curated RL directories (2 pts)
On X · well regarded, moderate buzz, from 11 posts about LiveBench in the last month
LiveBench is widely cited, including by Bloomberg Intelligence, for the US-China gap and DeepSeek V4.1 Flash, though some question its small agentic coding sample.
How we got to tier B
- Adoption: 43 models scored. Tier B.
- On X: well regarded, moderate buzz. “LiveBench is widely cited, including by Bloomberg Intelligence, for the US-China gap and DeepSeek V4.1 Flash, though some question its small agentic coding sample.” No move.
- In curated RL directories: 2 points, a floor of C.
- Not yet confirmed by a line from its own site or paper.
A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.
Not on the map yet: no line from its own site or paper places it in a domain.
Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-10-11 snapshot.