0

Mlebench

Frontier

MLE-Bench

Domain
rl-env
License
unknown
Published
Oct 2025

Cite

Notes

Only stored in your browser.

Attribution

Leaderboard scores
prime-hub
Attribution policy →

Top score 26.7% by GPT-4.1 Mini - 3 models reporting (3 frontier)

Score history

2
0%25%50%75%100%Apr 25May 25Jun 25Jul 25Aug 25GPT-4.1 Mini

Top models

3
MlebenchBar chart with 3 bars. Highest value: Claude Haiku 4 5 at 100.
3 models

Related tools

1
View all

Implementations, trainers, datasets and scaffolds linked to this eval.

FAQ

What is Mlebench?
MLE-Bench
What is the current top score on Mlebench?
The top reported score is 26.7% by GPT-4.1 Mini, across 3 models reporting (3 from frontier labs).
How can a model improve its Mlebench score?
Tools linked to Mlebench on Sophon include Mlebench RL Env (Community) - RL environments, datasets, and scaffolds that target this eval.
What license is Mlebench under?
Mlebench is available under unknown.