Coding benchmark
MLS-Bench Lite leaderboard
Every model the catalog carries a published MLS-Bench Lite value for, ranked by that value.
CategoryCoding
MeasureAgentic ML task evaluation
Tasks30 machine-learning research tasks
DifficultyML research and systems engineering
Published byMLS-Bench
A 30-task subset of MLS-Bench that evaluates whether AI systems can invent generalizable and scalable machine-learning methods.
MLS-Bench Lite ranking
3 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 |  Kimi K3 | Moonshot AI | 48.3 |
| 2 |  Qwen3.8 Max | Alibaba | 41.0 |
| 3 | Kimi K2.7 Code | 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.