BenchBench A
AI benchmark · Meta
What is BenchBench?
Benchmark Agreement Testing leaderboard that aggregates model scores across benchmarks and analyzes benchmark agreement/correlation under a standardized BAT methodology.
Tier A · a leaderboard, listed apart
Widely used: a lab reports it, or 50 or more models are scored on 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.
- 134 models scored
- in curated RL directories (1 pt)
On X · unclear, none buzz, from 2 posts about BenchBench in the last month
Recent posts using the name are jokes about benchmark proliferation, not discussion of the BAT leaderboard itself, so there is little signal.
How we got to tier A
- Adoption: 134 models scored. Tier A.
- On X: unclear, none buzz. “Recent posts using the name are jokes about benchmark proliferation, not discussion of the BAT leaderboard itself, so there is little signal.” No move.
- In curated RL directories: 1 point, a floor of none.
- Not yet confirmed by a line from its own site or paper.
- Judged a leaderboard, arena or index rather than one benchmark (or not a benchmark at all): listed apart.
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.