FLUB Benchmark

What is FLUB?

FLUB evaluates the reasoning and understanding abilities of LLMs. It includes three tasks with increasing difficulty, consisting of the tricky, humorous, and…

Released

2024-02-16

Evaluates

推理, Reasoning, NeurIPS 2024, 大语言模型, LLM, 逻辑推理, 不支持, Unsupported

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

FLUB paper and code

• Paper https://arxiv.org/abs/2402.11100
• Code https://github.com/THUKElab/FLUB

Which sources cite FLUB?

• FLUB

Related 推理, Reasoning, NeurIPS 2024, 大语言模型, LLM, 逻辑推理, 不支持, Unsupported benchmarks

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