openai/mle-bench
MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering
3 best points · 7 comments · 4 Hacker News posts · 1,792 GitHub stars · View on GitHub
Hacker News discussions
- Neo Scored 34.2% SOTA on OpenAI MLE-Bench (3 points, 0 comments, by vijgaurav, 2025-09-12)
- Neo (Autonomous ML engineer) is leading the MLE Bench with 34.2% score (2 points, 6 comments, by Vij137, 2025-08-19)
- Benchmark for measuring how well AI agents perform at ML engineering (1 points, 0 comments, by zerojames, 2024-10-09)
- Neo is leading the MLE Bench with 34.2% score (1 points, 1 comments, by gauravvij137, 2025-08-15)