Skip to main content
BenchLM

MLS-Bench Lite

We show this table for reference; we do not rank on it.

Data verified 34 confirmed releases in the last 30 daysFollow model changes

A 30-task subset of MLS-Bench that evaluates whether AI systems can invent generalizable and scalable machine-learning methods.

Benchmark score on MLS-Bench Lite — September 27, 2026

We compile the MLS-Bench Lite rows from provider self-reports. Kimi K3 leads the table at 48.3%, followed by Qwen3.8 Max (41.0%) and Step 5 Preview (40.5%). We do not use these results to rank models overall.

4 modelsCodingCurrentDisplay onlyUpdated September 27, 2026

Benchmark score table (4 models)

Score
1
Kimi K3Moonshot AI · Closed
48.3%
2
Qwen3.8 MaxAlibaba · Open weight
41.0%
3
Step 5 PreviewStepFun · Closed
40.5%
4
Kimi K2.7 CodeMoonshot AI · Open weight
35.1%

Among the reported MLS-Bench Lite rows, Kimi K3 is first at 48.3%. The third row is 7.8 points behind. The broader top-10 range is 13.2 points, so the table still separates the published systems.

4 models have been evaluated on MLS-Bench Lite. The benchmark falls in the Coding category. MLS-Bench Lite is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About MLS-Bench Lite

Year

2026

Tasks

30 machine-learning research tasks

Format

Agentic ML task evaluation

Difficulty

ML research and systems engineering

Moonshot reports MLS-Bench Lite as a coding-agent result for Kimi K2.7 Code. BenchLM stores the provider-reported exact value separately from weighted coding benchmarks because the row is a newly reported benchmark variant with sparse public model coverage.

Freshness and provenance

Version

MLS-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.

Questions

What does MLS-Bench Lite measure?

A 30-task subset of MLS-Bench that evaluates whether AI systems can invent generalizable and scalable machine-learning methods.

Which model scores highest on MLS-Bench Lite?

Kimi K3 by Moonshot AI currently leads with a score of 48.3% on MLS-Bench Lite.

How many models are evaluated on MLS-Bench Lite?

4 AI models have been evaluated on MLS-Bench Lite on BenchLM.

Last updated: September 27, 2026 · BenchLM version MLS-Bench Lite 2026

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 2,000+ readers.

One email each week. Unsubscribe anytime.