Human-Aligned Bench: Fine-Grained Assessment of Reasoning Ability in MLLMs vs. Humans
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912391603683328 |
|---|---|
| author | Qiu, Yansheng Xiao, Li Xu, Zhaopan Zhou, Pengfei Wang, Zheng Zhang, Kaipeng |
| author_facet | Qiu, Yansheng Xiao, Li Xu, Zhaopan Zhou, Pengfei Wang, Zheng Zhang, Kaipeng |
| contents | The goal of achieving Artificial General Intelligence (AGI) is to imitate humans and surpass them. Models such as OpenAI's o1, o3, and DeepSeek's R1 have demonstrated that large language models (LLMs) with human-like reasoning capabilities exhibit exceptional performance and are being gradually integrated into multimodal large language models (MLLMs). However, whether these models possess capabilities comparable to humans in handling reasoning tasks remains unclear at present. In this paper, we propose Human-Aligned Bench, a benchmark for fine-grained alignment of multimodal reasoning with human performance. Specifically, we collected 9,794 multimodal questions that solely rely on contextual reasoning, including bilingual (Chinese and English) multimodal questions and pure text-based questions, encompassing four question types: visual reasoning, definition judgment, analogical reasoning, and logical judgment. More importantly, each question is accompanied by human success rates and options that humans are prone to choosing incorrectly. Extensive experiments on the Human-Aligned Bench reveal notable differences between the performance of current MLLMs in multimodal reasoning and human performance. The findings on our benchmark provide insights into the development of the next-generation models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_11141 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Human-Aligned Bench: Fine-Grained Assessment of Reasoning Ability in MLLMs vs. Humans Qiu, Yansheng Xiao, Li Xu, Zhaopan Zhou, Pengfei Wang, Zheng Zhang, Kaipeng Computer Vision and Pattern Recognition Artificial Intelligence The goal of achieving Artificial General Intelligence (AGI) is to imitate humans and surpass them. Models such as OpenAI's o1, o3, and DeepSeek's R1 have demonstrated that large language models (LLMs) with human-like reasoning capabilities exhibit exceptional performance and are being gradually integrated into multimodal large language models (MLLMs). However, whether these models possess capabilities comparable to humans in handling reasoning tasks remains unclear at present. In this paper, we propose Human-Aligned Bench, a benchmark for fine-grained alignment of multimodal reasoning with human performance. Specifically, we collected 9,794 multimodal questions that solely rely on contextual reasoning, including bilingual (Chinese and English) multimodal questions and pure text-based questions, encompassing four question types: visual reasoning, definition judgment, analogical reasoning, and logical judgment. More importantly, each question is accompanied by human success rates and options that humans are prone to choosing incorrectly. Extensive experiments on the Human-Aligned Bench reveal notable differences between the performance of current MLLMs in multimodal reasoning and human performance. The findings on our benchmark provide insights into the development of the next-generation models. |
| title | Human-Aligned Bench: Fine-Grained Assessment of Reasoning Ability in MLLMs vs. Humans |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2505.11141 |