MLE-Bench (OpenAI) — leaderboard

75 Kaggle-style ML engineering competitions. Measures end-to-end ability to read, code, and submit solutions - graded against real human leaderboards.

Source: github.com.

Interactive version: theaggregate.ai/benchmark?slug=mle-bench-openai · How the rankings work · Data refreshed daily, snapshot 2026-07-22.