MLE-Bench Lite (Claude Code): leaderboard
FrontisAI OpenRSI's MLE-Bench Lite run — Kaggle-competition ML engineering with the Claude Code agent scaffold, 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. 2 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.8 | 63.64 | #39 |
| 2 | GLM-5.2 | 59.09 | #80 |
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-claude-code · How It Works · Data refreshed daily, snapshot 2026-11-05.