MLE-Bench
Progress Over Time
Interactive timeline showing model performance evolution on MLE-Bench
State-of-the-art frontier
Open
Proprietary
MLE-Bench Leaderboard
2 models
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Google | — | 1.0M | $1.50 / $7.50 | ||
| 2 | Google | — | 1.0M | $0.30 / $2.50 |
Notice missing or incorrect data?
What is MLE-Bench?
MLE-Bench evaluates AI agents on machine learning engineering tasks by measuring their performance on Kaggle competitions.
MLE-Bench is a text benchmark evaluating models on agents and code tasks. LLM Stats tracks 2 models on this benchmark, scored on a 0–1 scale. The current average is 0.5, with the leader at 0.6.
Compare leaders on the best AI for agents and best AI for code leaderboards.
Current leaders
Gemini 3.6 Flash from Google currently leads the MLE-Bench leaderboard with a score of 0.639 across 2 evaluated AI models.
FAQ
Common questions about the MLE-Bench benchmark and leaderboard.