LLMThinkBench

What is LLMThinkBench?

LLMThinkBench is a benchmark framework designed to evaluate large language models (LLMs) on basic math reasoning and “overthinking” behaviors, targeting…

Released

2025-07-05

Evaluates

推理, Reasoning, 数学, Math, 大语言模型, LLM, 逻辑推理, 数理能力, 不支持, Unsupported

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

LLMThinkBench paper and code

• Paper https://arxiv.org/abs/2507.04023
• Code https://github.com/ctrl-gaurav/LLMThinkBench

Which sources cite LLMThinkBench?

• LLMThinkBench

Related 推理, Reasoning, 数学, Math, 大语言模型, LLM, 逻辑推理, 数理能力, 不支持, Unsupported benchmarks

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