HellaSwag Benchmark

What is HellaSwag?

HellaSwag is a challenge dataset for evaluating commonsense natural language inference, which is specially hard for state-of-the-art models, though its…

Released

2019-05-19

Evaluates

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

Openness

restricted

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

HellaSwag paper and code

• Paper https://arxiv.org/abs/1905.07830
• Code https://github.com/rowanz/hellaswag

Which sources cite HellaSwag?

• HellaSwag

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

• A-OKVQA
• AbsPyramid
• ActiveFly-Bench
• Ada-LEval
• AdvancedMathBench
• AeroGround
• AFDBench
• AFFORDANCE20Q