SVAMP Benchmark

What is SVAMP?

SVAMP includes one-unknown arithmetic word problems with grade level up to 4 by applying simple variations over word problems in an existing dataset. SVAMP…

Released

2021-04-15

Evaluates

数学, Math, 大语言模型, LLM, 数理能力, 开源收录, Open-Source, 不支持, Unsupported

Openness

open

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

SVAMP paper, code and dataset

• Paper https://arxiv.org/pdf/2103.07191v2
• Code https://github.com/arkilpatel/SVAMP
• Dataset https://huggingface.co/datasets/ChilleD/SVAMP

Which sources cite SVAMP?

• SVAMP

Related 数学, Math, 大语言模型, LLM, 数理能力, 开源收录, Open-Source, 不支持, Unsupported benchmarks

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