Mlebench

Fresh

MLE-Bench

Type: RL Env
Tags: Tooluse
Runtime: multi-turn
License: unknown
Size: v0.2.0
Published: Oct 2025
Updated: Oct 2025
Canonical: app.primeintellect.ai/dashboard/environments/prime-creetz/mlebench

Cite

Notes

Only stored in your browser.

Attribution

README: api.primeintellect.ai/api/v1/environmentshub/prime-creetz/mlebench/@0.2.0/inspect
Scores: prime-hub

Attribution policy →

Public scores on this env

3

5 vf-eval reports across 3 models

1Claude 4.5 HaikuAnthropic100.0%2GPT-4.1 MiniOpenAI26.7%3GPT-5OpenAI10.0%

Open the scoring view →

Evals this tool implements

1

Same problem set, this tool's harness. Run it to score a model on the test.

MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering

OpenAI

Machine learning tasks drawn from 75 Kaggle competitions.

Contributors

1