MorphoBench: A Benchmark with Difficulty Adaptive to Model Reasoning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915557359484928 |
|---|---|
| author | Wang, Xukai Liu, Xuanbo Chen, Mingrui Zhong, Haitian Yang, Xuanlin Zeng, Bohan Hu, Jinbo Liang, Hao Niu, Junbo Li, Xuchen Wu, Ruitao An, Ruichuan Shi, Yang Liu, Liu Zhang, Xu-Yao Liu, Qiang Lin, Zhouchen Zhang, Wentao Dong, Bin |
| author_facet | Wang, Xukai Liu, Xuanbo Chen, Mingrui Zhong, Haitian Yang, Xuanlin Zeng, Bohan Hu, Jinbo Liang, Hao Niu, Junbo Li, Xuchen Wu, Ruitao An, Ruichuan Shi, Yang Liu, Liu Zhang, Xu-Yao Liu, Qiang Lin, Zhouchen Zhang, Wentao Dong, Bin |
| contents | With the advancement of powerful large-scale reasoning models, effectively evaluating the reasoning capabilities of these models has become increasingly important. However, existing benchmarks designed to assess the reasoning abilities of large models tend to be limited in scope and lack the flexibility to adapt their difficulty according to the evolving reasoning capacities of the models. To address this, we propose MorphoBench, a benchmark that incorporates multidisciplinary questions to evaluate the reasoning capabilities of large models and can adjust and update question difficulty based on the reasoning abilities of advanced models. Specifically, we curate the benchmark by selecting and collecting complex reasoning questions from existing benchmarks and sources such as Olympiad-level competitions. Additionally, MorphoBench adaptively modifies the analytical challenge of questions by leveraging key statements generated during the model's reasoning process. Furthermore, it includes questions generated using simulation software, enabling dynamic adjustment of benchmark difficulty with minimal resource consumption. We have gathered over 1,300 test questions and iteratively adjusted the difficulty of MorphoBench based on the reasoning capabilities of models such as o3 and GPT-5. MorphoBench enhances the comprehensiveness and validity of model reasoning evaluation, providing reliable guidance for improving both the reasoning abilities and scientific robustness of large models. The code has been released in https://github.com/OpenDCAI/MorphoBench. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_14265 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MorphoBench: A Benchmark with Difficulty Adaptive to Model Reasoning Wang, Xukai Liu, Xuanbo Chen, Mingrui Zhong, Haitian Yang, Xuanlin Zeng, Bohan Hu, Jinbo Liang, Hao Niu, Junbo Li, Xuchen Wu, Ruitao An, Ruichuan Shi, Yang Liu, Liu Zhang, Xu-Yao Liu, Qiang Lin, Zhouchen Zhang, Wentao Dong, Bin Artificial Intelligence With the advancement of powerful large-scale reasoning models, effectively evaluating the reasoning capabilities of these models has become increasingly important. However, existing benchmarks designed to assess the reasoning abilities of large models tend to be limited in scope and lack the flexibility to adapt their difficulty according to the evolving reasoning capacities of the models. To address this, we propose MorphoBench, a benchmark that incorporates multidisciplinary questions to evaluate the reasoning capabilities of large models and can adjust and update question difficulty based on the reasoning abilities of advanced models. Specifically, we curate the benchmark by selecting and collecting complex reasoning questions from existing benchmarks and sources such as Olympiad-level competitions. Additionally, MorphoBench adaptively modifies the analytical challenge of questions by leveraging key statements generated during the model's reasoning process. Furthermore, it includes questions generated using simulation software, enabling dynamic adjustment of benchmark difficulty with minimal resource consumption. We have gathered over 1,300 test questions and iteratively adjusted the difficulty of MorphoBench based on the reasoning capabilities of models such as o3 and GPT-5. MorphoBench enhances the comprehensiveness and validity of model reasoning evaluation, providing reliable guidance for improving both the reasoning abilities and scientific robustness of large models. The code has been released in https://github.com/OpenDCAI/MorphoBench. |
| title | MorphoBench: A Benchmark with Difficulty Adaptive to Model Reasoning |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2510.14265 |