Skip to main content

Benchmark profile

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.

Data verified

Benchmark score on MLE-Bench Lite — July 23, 2026

BenchLM mirrors the published score view for MLE-Bench Lite. MiniMax M2.7 leads the public snapshot at 66.6%. BenchLM does not use these results to rank models overall.

1 modelAgenticCurrentDisplay onlyUpdated July 23, 2026

Benchmark score table (1 model)

Score
1
MiniMax M2.7MiniMax · Open weight
66.6%

About MLE-Bench Lite

Year

2026

Tasks

Low-resource ML competitions

Format

Autonomous iterative ML optimization

Difficulty

Agentic machine learning

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.

BenchLM freshness & provenance

Version

MLE-Bench Lite 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

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?

MiniMax M2.7 by MiniMax currently leads with a score of 66.6% on MLE-Bench Lite.

How many models are evaluated on MLE-Bench Lite?

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

Last updated: July 23, 2026 · BenchLM version MLE-Bench Lite 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.