# MLS-Bench Lite leaderboard

Coding benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/leaderboards/benchmarks/coding-mls-bench-lite

Every model the catalog carries a published MLS-Bench Lite value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Coding |
| Measure | Agentic ML task evaluation |
| Tasks | 30 machine-learning research tasks |
| Difficulty | ML research and systems engineering |
| Published by | [MLS-Bench](https://mls-bench.com/) |

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

## MLS-Bench Lite ranking

4 models with a published MLS-Bench Lite value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Agentic ML task evaluation | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Kimi K3](https://modelscale.dev/models/kimi-3) | Moonshot AI | 48.3 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Qwen3.8 Max](https://modelscale.dev/models/qwen3-8-max) | Alibaba | 41.0 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Step 5 Preview](https://modelscale.dev/models/step-5-preview) | StepFun | 40.5 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Kimi K2.7 Code](https://modelscale.dev/models/kimi-k2-7-code) | Moonshot AI | 35.1 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
