MLE-bench (OpenAI): on 75 Kaggle competitions, the best AI agent setup (o1-preview with AIDE scaffolding) reaches at least the level of a bronze medal in 16.9% of competitions
translated by AI, reviewed by the editors
· Science · Software development
- technology
- Recursive self-improvement of AI
- source
- arxiv.org ↗
¶ cy9xfjiha