{"id":"mle-bench","name":"MLE-bench","maker":"OpenAI","url":"https://github.com/openai/mle-bench","repo":"openai/mle-bench","summary":"A benchmark of machine learning engineering competitions that tests whether agents can build models end to end.","details":"Uses a set of Kaggle competitions where an agent reads the task, prepares data, trains models and submits predictions, scored against the human leaderboard for each competition. The repository provides the setup and grading code.","open_source":true,"hosted":false,"verified":"2026-11-15","category":"benchmarks","category_name":"Agent benchmarks","page":"https://modelmoot.com/tools/mle-bench","reviewed":"2026-11-15","checked":{"at":"2026-11-15T15:07:43.409Z","address_answers":true},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}