MLE-bench

by OpenAI

Editor note

75 real Kaggle machine-learning competitions where an agent must prepare data, train models and submit results, scored against human leaderboard medal thresholds.

What it tests: End-to-end ML engineering: data prep, training, experimentation and submission quality.
Original source: github.com/openai/mle-bench
Last updated: Repo last commit 2026-04-24
License: Not checked yet — see source

Facts come only from the linked source (checked 15 Oct 2026). Credit belongs to the creators.

Reviews

No reviews yet.

Reviews from practitioners who sign in with GitHub open soon.