MLE-Bench Lite (Codex) — leaderboard
Metric: Medal Average (%). Source: frontisai.github.io. 2 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 68.18 |
| 2 | MiniMax-M3 | 54.55 |
Interactive version: theaggregate.ai/benchmark?slug=mle-bench-lite-codex · How It Works · Data refreshed daily, snapshot 2026-08-05.