MLE-Bench Lite (OpenMLE-Evo-Max): leaderboard
FrontisAI OpenRSI's MLE-Bench Lite run — Kaggle-competition ML engineering with OpenMLE-Evo-Max (experience priors plus asynchronous parallel search), 12-hour per-task budget on one RTX 4090; mean medal rate over the 22-task Lite split.
Metric: Medal Average (%). Source: frontisai.github.io. Saturation forecast: Around February 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Kimi K2.6 | 66.67 | #113 |
| 2 | GLM-5.2 | 66.67 | #80 |
| 3 | MiniMax-M3 | 65.15 | #151 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=mle-bench-lite-openmle-evo-max · How It Works · Data refreshed daily, snapshot 2026-11-05.