OSS-Bench

What is OSS-Bench?

OSS-Bench replaces functions with LLM-generated code and evaluates them using three natural metrics: compilability, functional correctness, and memory safety…

Released

2025-06-30

Evaluates

代码, Code, Memory Safety, Open-Source Software, Living Benchmark, 大语言模型, LLM, 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/OSS-Bench

OSS-Bench paper and code

• Paper https://arxiv.org/abs/2505.12331
• Code https://github.com/oss-bench/oss-bench

Which sources cite OSS-Bench?

• OSS-Bench

Related 代码, Code, Memory Safety, Open-Source Software, Living Benchmark, 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