RedCode Benchmark

What is RedCode?

RedCode provides comprehensive and practical evaluations on the safety of code agents, including 4,050 risky test cases covering 25 types of critical…

Released

2024-11-12

Evaluates

安全, Safety, 智能体, Agent, 任务执行, Task Execution, 安全对齐, Safety Alignment, 不支持, Unsupported

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

RedCode paper and code

• Paper https://arxiv.org/abs/2411.07781
• Code https://github.com/AI-secure/RedCode

Which sources cite RedCode?

• RedCode

Related 安全, Safety, 智能体, Agent, 任务执行, Task Execution, 安全对齐, Safety Alignment, 不支持, Unsupported benchmarks

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