GR-Ben: A General Reasoning Benchmark for Evaluating Process Reward Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917466275315712 |
|---|---|
| author | Sun, Zhouhao Zhang, Xuan Ding, Xiao Cai, Bibo Du, Li Xiong, Kai Dai, Xinran Zhang, Fei tang, weidi Kan, Zhiyuan Zhao, Yang Qin, Bing Liu, Ting |
| author_facet | Sun, Zhouhao Zhang, Xuan Ding, Xiao Cai, Bibo Du, Li Xiong, Kai Dai, Xinran Zhang, Fei tang, weidi Kan, Zhiyuan Zhao, Yang Qin, Bing Liu, Ting |
| contents | Currently, process reward models (PRMs) have exhibited remarkable potential for test-time scaling. Since large language models (LLMs) regularly generate flawed intermediate reasoning steps when tackling a broad spectrum of reasoning and decision-making tasks, PRMs are required to possess capabilities for detecting process-level errors in real-world scenarios. However, existing benchmarks primarily focus on mathematical reasoning, thereby failing to comprehensively evaluate the error detection ability of PRMs across diverse reasoning scenarios. To mitigate this gap, we introduce GR-Ben, a process-level benchmark specifically designed for assessing PRM's performance across two primary reasoning domains (science and logic) and nine subdomains. We conduct extensive experiments on a diverse set of 22 models, encompassing both PRMs and LLMs, and derive two key findings: (1) In domains beyond mathematical reasoning, the error-detection ability of existing PRMs and LLMs is found to be markedly weaker by comparison.(2) In general, PRMs are less adept at identifying knowledge-based errors, whereas LLMs exhibit poorer performance in detecting computational errors. We hope GR-Ben can foster future researches on PRMs for general domains, thereby enhancing the reasoning capabilities of LLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_01203 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GR-Ben: A General Reasoning Benchmark for Evaluating Process Reward Models Sun, Zhouhao Zhang, Xuan Ding, Xiao Cai, Bibo Du, Li Xiong, Kai Dai, Xinran Zhang, Fei tang, weidi Kan, Zhiyuan Zhao, Yang Qin, Bing Liu, Ting Artificial Intelligence Computation and Language Currently, process reward models (PRMs) have exhibited remarkable potential for test-time scaling. Since large language models (LLMs) regularly generate flawed intermediate reasoning steps when tackling a broad spectrum of reasoning and decision-making tasks, PRMs are required to possess capabilities for detecting process-level errors in real-world scenarios. However, existing benchmarks primarily focus on mathematical reasoning, thereby failing to comprehensively evaluate the error detection ability of PRMs across diverse reasoning scenarios. To mitigate this gap, we introduce GR-Ben, a process-level benchmark specifically designed for assessing PRM's performance across two primary reasoning domains (science and logic) and nine subdomains. We conduct extensive experiments on a diverse set of 22 models, encompassing both PRMs and LLMs, and derive two key findings: (1) In domains beyond mathematical reasoning, the error-detection ability of existing PRMs and LLMs is found to be markedly weaker by comparison.(2) In general, PRMs are less adept at identifying knowledge-based errors, whereas LLMs exhibit poorer performance in detecting computational errors. We hope GR-Ben can foster future researches on PRMs for general domains, thereby enhancing the reasoning capabilities of LLMs. |
| title | GR-Ben: A General Reasoning Benchmark for Evaluating Process Reward Models |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2605.01203 |