GSM1k Benchmark

What is GSM1k?

GSM1k is meant for evaluating LLM's math reasoning ability. It mirrors the style and complexity of the established GSM8k benchmark while consider the problem…

Released

2024-05-01

Evaluates

数学, Math, NeurIPS 2024, 大语言模型, LLM, 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/GSM1k

GSM1k paper and code

• Paper https://arxiv.org/abs/2405.00332
• Code https://github.com/scaleapi/gsm1k_eval

Which sources cite GSM1k?

• GSM1k

Related 数学, Math, NeurIPS 2024, 大语言模型, LLM, 数理能力, 不支持, Unsupported benchmarks

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