Evaluation

MLE-Bench

Agent's ability to solve Kaggle challenges

Autonomy & self-improvement OpenAI

How it was run

Open a release to see the setup, scoring, and other details that the lab published. Only fields the lab actually disclosed are shown.

o1 Dec 2024

OpenAI

rich detail 15 method fields published

See how this test was run

o3-mini Jan 2025

OpenAI

rich detail 15 method fields published

See how this test was run

Deep Research Feb 2025

OpenAI

rich detail 15 method fields published

See how this test was run

GPT-4.5 Feb 2025

OpenAI

rich detail 16 method fields published

See how this test was run