Agentic Coding Benchmark

MLS-Bench

MLS-Bench - machine learning systems agent benchmark (e.g. safe-RL constraint-handling mechanism design). Scores are measured over the MLS-Bench-Tasks dataset (https://huggingface.co/datasets/Bohan22/MLS-Bench-Tasks); official site: https://mls-bench.com/.

Category

Agentic Coding

Score type

percent

Scale

100%

higher is better

Models tested

3

What is MLS-Bench?

MLS-Bench is a benchmark for how well a model works as an autonomous coding agent. The official description says: "MLS-Bench - machine learning systems agent benchmark (e.g". Below we describe in simple words what benchmarks of this type generally examine.

What does it test?

MLS-Bench measures how well a model works as an autonomous coding agent. In detail, it checks:

  • fixing real, open bugs from real software repositories
  • planning multi-step changes, running commands and editing files by itself
  • passing the project's test suite after its changes
  • handling whole repositories, not just small isolated code snippets

How to read the score

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better.

Official methodology note: MLS-Bench - machine learning systems agent benchmark (e.g. safe-RL constraint-handling mechanism design). Scores are measured over the MLS-Bench-Tasks dataset (https://huggingface.co/datasets/Bohan22/MLS-Bench-Tasks); official site: https://mls-bench.com/.

Frequently asked questions

What is the MLS-Bench benchmark?

MLS-Bench is a benchmark for how well a model works as an autonomous coding agent. The official description says: 'MLS-Bench - machine learning systems agent benchmark (e.g'. Below we describe in simple words what benchmarks of this type generally examine.

What does MLS-Bench test?

MLS-Bench mainly measures how well a model works as an autonomous coding agent. Concretely, it checks: fixing real, open bugs from real software repositories; planning multi-step changes, running commands and editing files by itself; passing the project's test suite after its changes.

How is the MLS-Bench score calculated?

The score is accuracy: the percentage of tasks answered or solved correctly. 100% means every task was solved perfectly; higher is better. The declared maximum score of this benchmark is 100.0.

Where do I get MLS-Bench data and scores?

The official source is https://huggingface.co/datasets/Bohan22/MLS-Bench-Tasks. The official benchmark page/reference is linked on this page. Every score on Open LLM Radar is also available as open data: download the scores JSON (http://open-llm-radar-api:8000/api/v1/benchmarks/mls-bench/scores) or pull it directly from the Open LLM Radar API with any HTTP client.

Model scores 3 models tested

Reset
# Model Score Date Source Verified
1 DeepSeek-V4.1-Flash-1017
DeepSeek
44.3%
— Report Unverified
2 Sage-S2.1-Flash
Shanghai AI Laboratory
42%
— Report Verified
3 GLM-5.3-Flash
Zhipu AI
39.9%
— Report Unverified

What now?

You've seen how models score on MLS-Bench — here's what to do next.