Benchmark
MLE-bench
What is MLE-bench?
Kaggle-derived ML engineering tasks; wall-clock budget and hardware are part of the result. Published by OpenAI.
- Released
- 2024-10-09
- Evaluates
- ai research
- Openness
- unknown
- Importer
- Model reports
- Reported scores
- 0
Source provenance
- Original evidence https://openai.com/index/mle-bench/
MLE-bench links
No reported scores are on record for this benchmark yet.
Which sources cite MLE-bench?
- GPT-5.6 (Sol, Terra, Luna) OpenAI, 2026-07-09
- GPT-5 OpenAI, 2025-08-07