ProcessBench

What is ProcessBench?

ProcessBench can measure the ability to identify erroneous steps in mathematical reasoning. It consists of 3,400 test cases, primarily focused on competition-…

Released

2024-12-10

Evaluates

学科, Examination, 推理, Reasoning, 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/ProcessBench

ProcessBench paper, code and dataset

• Paper https://arxiv.org/abs/2412.06559
• Code https://github.com/QwenLM/ProcessBench
• Dataset https://huggingface.co/datasets/Qwen/ProcessBench

Which sources cite ProcessBench?

• ProcessBench

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

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