UTBoost Benchmark

What is UTBoost?

UTBoost generates unit tests using LLMs to augment the test cases for certain instances in SWE-Bench, enabling a more rigorous use of SWE-Bench to evaluate the…

Released

2025-06-10

Evaluates

代码, Code, Code Agent, SWE-Bench, Automatic test augmentation, 智能体, Agent, 代码工程, 不支持, Unsupported

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

• Original evidence https://hub.opencompass.org.cn/dataset-detail/UTBoost

UTBoost paper and code

• Paper https://arxiv.org/abs/2506.09289
• Code https://github.com/CUHK-Shenzhen-SE/UTBoost

Which sources cite UTBoost?

• UTBoost

Related 代码, Code, Code Agent, SWE-Bench, Automatic test augmentation, 智能体, Agent, 代码工程, 不支持, Unsupported benchmarks

• A-Bench
• A-OKVQA
• AbsPyramid
• ActionAtlas
• Ada-LEval
• AECBench
• AFQMC
• AgentBoard