LongBench

What is LongBench?

LongBench is a benchmark for bilingual, multitask, and comprehensive assessment of long context understanding capabilities of large language models.

Released

2023-08-28

Evaluates

长文本, Long-Context, ACL 2024, 大语言模型, LLM, 长上下文, Long Context, 开源收录, Open-Source, 不支持, Unsupported

Openness

restricted

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

LongBench paper, code and dataset

• Paper https://arxiv.org/pdf/2308.14508.pdf
• Code https://github.com/THUDM/LongBench
• Dataset https://huggingface.co/datasets/THUDM/LongBench

Which sources cite LongBench?

• LongBench

Related 长文本, Long-Context, ACL 2024, 大语言模型, LLM, 长上下文, Long Context, 开源收录, Open-Source, 不支持, Unsupported benchmarks

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