DROP Benchmark

What is DROP?

DROP is a QA dataset which tests comprehensive understanding of paragraphs. In this crowdsourced, adversarially-created, 96k question-answering benchmark, a…

Released

2019-03-01

Evaluates

推理, Reasoning, 大语言模型, LLM, 逻辑推理, 开源收录, Open-Source, 不支持, Unsupported

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

DROP paper and code

• Paper https://arxiv.org/abs/1903.00161
• Code https://github.com/allenai/allennlp-reading-comprehension

Which sources cite DROP?

• DROP

Related 推理, Reasoning, 大语言模型, LLM, 逻辑推理, 开源收录, Open-Source, 不支持, Unsupported benchmarks

• A-Bench
• A-OKVQA
• AbsPyramid
• ActionAtlas
• ActiveFly-Bench
• Ada-LEval
• AdvancedMathBench
• AECBench