SWE-bench-Live

What is SWE-bench-Live?

SWE-bench-Live is a live-updatable benchmark designed for evaluating large language models (LLMs) and agents on real-world software issue resolution tasks.

Released

2025-06-01

Evaluates

代码, Code, 智能体, Agent, 任务执行, Task Execution, 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/SWE-bench-Live

SWE-bench-Live paper

• Paper https://arxiv.org/abs/2505.23419

Which sources cite SWE-bench-Live?

• SWE-bench-Live

Related 代码, Code, 智能体, Agent, 任务执行, Task Execution, 代码工程, 不支持, Unsupported benchmarks

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