DebugBench

What is DebugBench?

DebugBench is an LLM debugging benchmark consisting of 4,253 instances. It covers four major bug categories and 18 minor types in C++, Java, and Python.

Released

2024-08-11

Evaluates

代码, Code, ACL 2024, 大语言模型, LLM, 代码工程, 不支持, Unsupported

Openness

open

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

DebugBench code and dataset

• Code https://github.com/thunlp/DebugBench
• Dataset https://huggingface.co/datasets/Rtian/DebugBench

Which sources cite DebugBench?

• DebugBench

Related 代码, Code, ACL 2024, 大语言模型, LLM, 代码工程, 不支持, Unsupported benchmarks

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