MLE-bench

Evals

Benchmark / dataset

75 Kaggle ML-engineering competitions for agents.

Category
Autonomy, R&D & self-replication
Insurance exposure
Unmapped
Publisher
OpenAI
Publisher type
Frontier lab
License
MIT
Status
Maintained (<12mo)
Last commit
2026-04-24
Stars
1775

View source on GitHub →

Wanich Risk Lab, 2026.