# MLE-Bench Lite

> A lightweight machine-learning competition benchmark that measures whether models can iteratively train, evaluate, and improve ML systems in low-resource settings.

Canonical page: https://benchlm.ai/benchmarks/mle-bench-lite

- Category: [Agentic](/agentic)
- Last updated: September 27, 2026

## About MLE-Bench Lite

- Year: 2026
- Tasks: Low-resource ML competitions
- Format: Autonomous iterative ML optimization
- Difficulty: Agentic machine learning
- Paper: [MiniMax M2.7: Early Echoes of Self-Evolution](https://www.minimax.io/news/minimax-m27-en)

MiniMax reports MLE-Bench Lite results from autonomous multi-round optimization on low-resource machine-learning competitions, making it a useful signal for agentic ML workflows.

MLE-Bench Lite is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (3 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [Atria Dawn Preview](/models/atria-dawn-preview) | Shanghai Artificial Intelligence Laboratory | 86.2% |
| 2 | [MiniMax M2.7](/models/minimax-m2-7) | MiniMax | 66.6% |
| 3 | [Agents-A1-4B](/models/agents-a1-4b) | InternScience | 22.7% |

## FAQ

### What does MLE-Bench Lite measure?

A lightweight machine-learning competition benchmark that measures whether models can iteratively train, evaluate, and improve ML systems in low-resource settings.

### Which model scores highest on MLE-Bench Lite?

Atria Dawn Preview by Shanghai Artificial Intelligence Laboratory currently leads with a score of 86.2% on MLE-Bench Lite.

### How many models are evaluated on MLE-Bench Lite?

3 AI models have been evaluated on MLE-Bench Lite on BenchLM.

### Does MLE-Bench Lite affect BenchLM's overall score?

Not directly. MLE-Bench Lite is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Compare Top Models on MLE-Bench Lite

- [Atria Dawn Preview vs MiniMax M2.7](/compare/atria-dawn-preview-vs-minimax-m2-7)
- [MiniMax M2.7 vs Agents-A1-4B](/compare/agents-a1-4b-vs-minimax-m2-7)