RExBench

What is RExBench?

RExBench is a benchmark for evaluating large language model agents’ ability to autonomously implement AI research extensions, focusing on code generation…

Released

2025-06-27

Evaluates

代码, Code, 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/RExBench

RExBench paper, code and dataset

• Paper https://img.shields.io/badge/arXiv-arXiv:2506.22598-b31b1b.svg
• Code https://github.com/tinlaboratory/RexBench
• Dataset https://huggingface.co/datasets/tin-lab/RExBench

Which sources cite RExBench?

• RExBench

Related 代码, Code, 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