{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/benchmarking-multi-image-understanding-in","title":"Benchmarking Multi-Image Understanding in Vision and Language Models: Perception, Knowledge, Reasoning, and Multi-Hop Reasoning","arxiv_id":"2406.12742","date":"2024-06-18","proceeding":null,"authors":["Bingchen Zhao","Yongshuo Zong","Letian Zhang","Timothy Hospedales"],"abstract":"The advancement of large language models (LLMs) has significantly broadened the scope of applications in natural language processing, with multi-modal LLMs extending these capabilities to integrate and interpret visual data. However, existing benchmarks for visual language models (VLMs) predominantly focus on single-image inputs, neglecting the crucial aspect of multi-image understanding. In this paper, we introduce a Multi-Image Relational Benchmark MIRB, designed to evaluate VLMs' ability to compare, analyze, and reason across multiple images. Our benchmark encompasses four categories: perception, visual world knowledge, reasoning, and multi-hop reasoning. Through a comprehensive evaluation of a wide range of open-source and closed-source models, we demonstrate that while open-source VLMs were shown to approach the performance of GPT-4V in single-image tasks, a significant performance gap remains in multi-image reasoning tasks. Our findings also reveal that even the state-of-the-art GPT-4V model struggles with our benchmark, underscoring the need for further research and development in this area. We believe our contribution of MIRB could serve as a testbed for developing the next-generation multi-modal models.","url_abs":"https://arxiv.org/abs/2406.12742v1","url_pdf":"https://arxiv.org/pdf/2406.12742v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"benchmarking-multi-image-understanding-in","repo_url":"https://github.com/dtennant/mirb_eval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"world-knowledge","task_name":"World Knowledge"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2406.12742","atlas_url":"https://app.syntology.ai/?focus=2406.12742","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12742"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dtennant/mirb_eval","reach":{"status":"ok"}}],"summary":{"ran":3,"unverified":3},"by_repo_kind":{"official":{"samples":6,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":6,"samples":[{"code_sha256_prefix":"832d5daf1ddc2e31","entry":"load_data","repo":"dtennant/mirb_eval","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/dtennant/mirb_eval/blob/HEAD/utils/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"832d5daf1ddc2e31"}},{"code_sha256_prefix":"2a0bf8b452c624f0","entry":"load_image","repo":"dtennant/mirb_eval","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/dtennant/mirb_eval/blob/HEAD/utils/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2a0bf8b452c624f0"}},{"code_sha256_prefix":"d55cfede35824b77","entry":"truncate_prediction","repo":"dtennant/mirb_eval","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/dtennant/mirb_eval/blob/HEAD/utils/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d55cfede35824b77"}},{"code_sha256_prefix":"26a3969443524a09","entry":"I2T_first_prob","repo":"dtennant/mirb_eval","repo_kind":"official","path":"utils/model_inference.py","file_url":"https://github.com/dtennant/mirb_eval/blob/HEAD/utils/model_inference.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"26a3969443524a09"}},{"code_sha256_prefix":"1885af4685aa7100","entry":"ICL_I2T_inference","repo":"dtennant/mirb_eval","repo_kind":"official","path":"utils/model_inference.py","file_url":"https://github.com/dtennant/mirb_eval/blob/HEAD/utils/model_inference.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1885af4685aa7100"}},{"code_sha256_prefix":"faa3448b4396a140","entry":"load_i2t_model","repo":"dtennant/mirb_eval","repo_kind":"official","path":"utils/load_models.py","file_url":"https://github.com/dtennant/mirb_eval/blob/HEAD/utils/load_models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"faa3448b4396a140"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}