MathBench

What is MathBench?

MathBench, a new benchmark that rigorously assesses the mathematical capabilities of large language models. MathBench spans a wide range of mathematical…

Released

2024-08-11

Evaluates

数学, Math, 大语言模型, LLM, 数理能力, 官方自建, Official, 不支持, Unsupported

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

MathBench code

• Code https://github.com/open-compass/MathBench

Which sources cite MathBench?

• MathBench

Related 数学, Math, 大语言模型, LLM, 数理能力, 官方自建, Official, 不支持, Unsupported benchmarks

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