PRMBench_Preview

What is PRMBench_Preview?

PRMBench is a benchmark dataset for evaluating process-level reward models (PRMs). It consists of 6,216 data instances, each containing a question, a solution…

Released

2025-01-06

Evaluates

学科, Examination, 大语言模型, LLM, 数理能力, Math, 不支持, Unsupported

Openness

open

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

PRMBench_Preview paper, code and dataset

• Paper https://arxiv.org/abs/2501.03124
• Code https://github.com/ssmisya/PRMBench
• Dataset https://huggingface.co/datasets/hitsmy/PRMBench_Preview

Which sources cite PRMBench_Preview?

• PRMBench_Preview

Related 学科, Examination, 大语言模型, LLM, 数理能力, Math, 不支持, Unsupported benchmarks

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