What it measures
- ML engineering
- Experiment execution
- Competition-style optimization
MLE-bench
A machine-learning engineering benchmark based on Kaggle-style competition tasks.
How to read the score
medal or score; higher is better.
Sourced Ranking
| Rank | Model | Provider | Score | Source | Source Type | Verified |
|---|
Limitations
- Do not assume the GitHub repository is a live leaderboard.
- The arXiv paper is static; GitHub has newer repository and leaderboard notes.
- GitHub notes that leaderboard submissions are paused; newer scores may appear in model release pages.
leaderboard
OpenAI MLE-bench GitHub repository
The arXiv paper is static; GitHub has newer repository and leaderboard notes. GitHub notes that leaderboard submissions are paused; newer scores may appear in model release pages.
paper
MLE-bench paper or specification
Use for benchmark definition, not necessarily for latest model scores.
third-party
MLE-bench dataset or code
Use for dataset, code, or implementation details; score freshness depends on the benchmark.