Benchmark

MLE-Bench

MLE-Bench evaluates AI agents on machine learning engineering tasks by measuring their performance on Kaggle competitions.

Modality
text
Categories
agents, code
Openness
unknown
Source
llm_stats
Reported scores
2

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
Gemini 3.5 Flash-LiteGoogle0.3922026-07-21evidence
Gemini 3.6 FlashGoogle0.6392026-07-21evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.