paper-with-me

홈 › Papers

OMIBench: Benchmarking Olympiad-Level Multi-Image Reasoning in Large Vision-Language Model

2026-04-22 · Qiguang Chen, Chengyu Luan, Jiajun Wu, Qiming Yu, Yi Yang, Yizhuo Li, Jingqi Tong, Xiachong Feng, Libo Qin, Wanxiang Che arxiv

Large vision-language models (LVLMs) have made substantial advances in reasoning tasks at the Olympiad level. Nevertheless, current Olympiad-level multimodal reasoning benchmarks for these models often emphasize single-image analysis and fail to exploit contextual information across multiple images. We present OMIBench, a benchmark designed to evaluate Olympiad-level reasoning when the required evidence is distributed over multiple images. It contains problems from biology, chemistry, mathematics, and physics Olympiads, together with manually annotated rationales and evaluation protocols for both exact and semantic answer matching. Across extensive experiments on OMIBench, we observe meaningful performance gaps in existing models. Even the strongest LVLMs, such as Gemini-3-Pro, attain only about 50% on the benchmark. These results position OMIBench as a focused resources for studying and improving multi-image reasoning in LVLMs.

📄 PDF Abstract BibTeX arXiv:2604.20806

Code (0)

등록된 구현이 없습니다.

Tasks

Multimodal Reasoning

Similar Papers 제목 키워드 기반

RIMO: An Easy-to-Evaluate, Hard-to-Solve Olympiad Benchmark for Advanced Mathematical Reasoning

2025-09-09 · Ziye Chen, Chengwei Qin, Yao Shu arxiv

As large language models (LLMs) reach high scores on established mathematical benchmarks, such as GSM8K and MATH, the research community has turned to International Mathematical Olympiad (IMO) problems to push the evalua…

Mathematical Reasoning

Benchmarking Foundation Models with Retrieval-Augmented Generation in Olympic-Level Physics Problem Solving

2025-10-01 · Shunfeng Zheng, Yudi Zhang, Meng Fang, Zihan Zhang 외 arxiv

Retrieval-augmented generation (RAG) with foundation models has achieved strong performance across diverse tasks, but their capacity for expert-level reasoning-such as solving Olympiad-level physics problems-remains larg…

OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems

2024-02-21 · Chaoqun He, Renjie Luo, Yuzhuo Bai, Shengding Hu 외

Recent advancements have seen Large Language Models (LLMs) and Large Multimodal Models (LMMs) surpassing general human capabilities in various tasks, approaching the proficiency level of human experts across multiple dom…

Logical Fallacies

Proving Olympiad Algebraic Inequalities without Human Demonstrations

2024-06-20 · Chenrui Wei, Mengzhou Sun, Wei Wang

Solving Olympiad-level mathematical problems represents a significant advancement in machine intelligence and automated reasoning. Current machine learning methods, however, struggle to solve Olympiad-level problems beyo…

Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models

2024-10-10 · Bofei Gao, Feifan Song, Zhe Yang, Zefan Cai 외

Recent advancements in large language models (LLMs) have led to significant breakthroughs in mathematical reasoning capabilities. However, existing benchmarks like GSM8K or MATH are now being solved with high accuracy (e…

GSM8KMathMathematical Reasoning