Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Coding benchmark
Every model the catalog carries a published MLS-Bench Lite value for, ranked by that value.
A 30-task subset of MLS-Bench that evaluates whether AI systems can invent generalizable and scalable machine-learning methods. 4 models in the ModelScale catalog have a published value.
Each point is a model with a published MLS-Bench Lite value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
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 |
|---|---|---|---|
| 1 | Moonshot AI | 48.3 | |
| 2 | Alibaba | 41.0 | |
| 3 | StepFun | 40.5 |
What the benchmark measures and how its value is published, from the source’s own record.
MLS-Bench Lite is a coding benchmark published by MLS-Bench. A 30-task subset of MLS-Bench that evaluates whether AI systems can invent generalizable and scalable machine-learning methods. Its evaluation set is described by the source as 30 machine-learning research tasks. The source rates its difficulty as ML research and systems engineering.
Each model's result is published by MLS-Bench as agentic ML task evaluation. ModelScale prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 4 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.
| 4 | Moonshot AI | 35.1 |
Evidence key: Observed
Rows are ordered by the value MLS-Bench published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.