← Benchmarks
MLE-Bench Lite
MLE-Bench Lite evaluates AI agents on machine learning engineering tasks, testing their ability to build, train, and optimize ML models for Kaggle-style competitions in a lightweight evaluation format.
id mle-bench-lite · max 1 · 2 models reported
| # | Model | Score |
|---|---|---|
| 1 | Atria Dawn Preview Shanghai AI Laboratory · open | 0.86 |