MLE-bench A
AI benchmark · Self Improvement
- Publisher
- OpenAI Evals
- Domains
- Self Improvement
- Tier
- A why
- Snapshot
What is MLE-bench?
Kaggle-style machine learning engineering tasks covering training, data preparation, and experiments.
Tier A
A
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.
- 2 models scored
- reported by OpenAI
- in curated RL directories (1 pt)
On X · well regarded, moderate buzz, from 4 posts about MLE-bench in the last month
MLE-bench is cited as a reference benchmark for autonomous ML agents, with Meta's AIRA-2, Microsoft's R&D-Agent and Atria reporting results on it.
How we got to tier A
- Adoption: 2 models scored; reported by OpenAI. Tier A.
- On X: well regarded, moderate buzz. “MLE-bench is cited as a reference benchmark for autonomous ML agents, with Meta's AIRA-2, Microsoft's R&D-Agent and Atria reporting results on it.” No move.
- In curated RL directories: 1 point, a floor of none.
- 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.