Loading…

Tools

Friends

Community

A Webioinfo project · directory data from multiple sources · live metrics from the GitHub API · benchmark observations located via Benchmark Radar

MLE-bench

openai/mle-bench

Stable

MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering

Overview

MLE-bench is a benchmarks AI agent developed by openai with 1.8k GitHub stars, written in Python, currently Stable.

MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering

GitHub metrics refresh daily — last fetched today.

Jun Shern Chan, Neil Chowdhury, Oliver Jaffe, James Aung, Dane Sherburn, E. Mays … Lilian Weng, Aleksander Madry

No verified run reviews yet. Be the first to run MLE-bench and report.

No reviews yet. Reviews from researchers who actually ran MLE-bench are what this platform is for.