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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Qiguang, Luan, Chengyu, Wu, Jiajun, Yu, Qiming, Yang, Yi, Li, Yizhuo, Tong, Jingqi, Feng, Xiachong, Qin, Libo, Che, Wanxiang
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917429840445440
author Chen, Qiguang
Luan, Chengyu
Wu, Jiajun
Yu, Qiming
Yang, Yi
Li, Yizhuo
Tong, Jingqi
Feng, Xiachong
Qin, Libo
Che, Wanxiang
author_facet Chen, Qiguang
Luan, Chengyu
Wu, Jiajun
Yu, Qiming
Yang, Yi
Li, Yizhuo
Tong, Jingqi
Feng, Xiachong
Qin, Libo
Che, Wanxiang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_20806
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle OMIBench: Benchmarking Olympiad-Level Multi-Image Reasoning in Large Vision-Language Model
Chen, Qiguang
Luan, Chengyu
Wu, Jiajun
Yu, Qiming
Yang, Yi
Li, Yizhuo
Tong, Jingqi
Feng, Xiachong
Qin, Libo
Che, Wanxiang
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
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.
title OMIBench: Benchmarking Olympiad-Level Multi-Image Reasoning in Large Vision-Language Model
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2604.20806