{"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/we-math-does-your-large-multimodal-model","title":"We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?","arxiv_id":"2407.01284","date":"2024-07-01","proceeding":null,"authors":["Runqi Qiao","Qiuna Tan","Guanting Dong","Minhui Wu","Chong Sun","Xiaoshuai Song","Zhuoma Gongque","Shanglin Lei","Zhe Wei","Miaoxuan Zhang","Runfeng Qiao","Yifan Zhang","Xiao Zong","Yida Xu","Muxi Diao","Zhimin Bao","Chen Li","Honggang Zhang"],"abstract":"Visual mathematical reasoning, as a fundamental visual reasoning ability, has received widespread attention from the Large Multimodal Models (LMMs) community. Existing benchmarks, such as MathVista and MathVerse, focus more on the result-oriented performance but neglect the underlying principles in knowledge acquisition and generalization. Inspired by human-like mathematical reasoning, we introduce WE-MATH, the first benchmark specifically designed to explore the problem-solving principles beyond end-to-end performance. We meticulously collect and categorize 6.5K visual math problems, spanning 67 hierarchical knowledge concepts and five layers of knowledge granularity. We decompose composite problems into sub-problems according to the required knowledge concepts and introduce a novel four-dimensional metric, namely Insufficient Knowledge (IK), Inadequate Generalization (IG), Complete Mastery (CM), and Rote Memorization (RM), to hierarchically assess inherent issues in LMMs' reasoning process. With WE-MATH, we conduct a thorough evaluation of existing LMMs in visual mathematical reasoning and reveal a negative correlation between solving steps and problem-specific performance. We confirm the IK issue of LMMs can be effectively improved via knowledge augmentation strategies. More notably, the primary challenge of GPT-4o has significantly transitioned from IK to IG, establishing it as the first LMM advancing towards the knowledge generalization stage. In contrast, other LMMs exhibit a marked inclination towards Rote Memorization - they correctly solve composite problems involving multiple knowledge concepts yet fail to answer sub-problems. We anticipate that WE-MATH will open new pathways for advancements in visual mathematical reasoning for LMMs. The WE-MATH data and evaluation code are available at https://github.com/We-Math/We-Math.","url_abs":"https://arxiv.org/abs/2407.01284v1","url_pdf":"https://arxiv.org/pdf/2407.01284v1.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":"we-math-does-your-large-multimodal-model","repo_url":"https://github.com/we-math/we-math","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"math","task_name":"Math"},{"task_slug":"mathematical-reasoning","task_name":"Mathematical Reasoning"},{"task_slug":"memorization","task_name":"Memorization"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"focus","method_name":"Focus"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.01284","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01284"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/we-math/we-math","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":5},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":5,"samples":[{"code_sha256_prefix":"4008b2c1e4467468","entry":"evaluate_steps","repo":"we-math/we-math","repo_kind":"official","path":"evaluation/accuracy.py","file_url":"https://github.com/we-math/we-math/blob/HEAD/evaluation/accuracy.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4008b2c1e4467468"}},{"code_sha256_prefix":"37ee16ed64ec3266","entry":"evaluate_steps","repo":"we-math/we-math","repo_kind":"official","path":"evaluation/four_dimensional_metrics.py","file_url":"https://github.com/we-math/we-math/blob/HEAD/evaluation/four_dimensional_metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"37ee16ed64ec3266"}},{"code_sha256_prefix":"fc2faee35eb314f1","entry":"load_and_process_data","repo":"we-math/we-math","repo_kind":"official","path":"evaluation/accuracy.py","file_url":"https://github.com/we-math/we-math/blob/HEAD/evaluation/accuracy.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fc2faee35eb314f1"}},{"code_sha256_prefix":"61e86a3928537279","entry":"load_knowledge_structure_nodes","repo":"we-math/we-math","repo_kind":"official","path":"evaluation/accuracy.py","file_url":"https://github.com/we-math/we-math/blob/HEAD/evaluation/accuracy.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"61e86a3928537279"}},{"code_sha256_prefix":"9f722ab626794328","entry":"process_steps_data","repo":"we-math/we-math","repo_kind":"official","path":"evaluation/four_dimensional_metrics.py","file_url":"https://github.com/we-math/we-math/blob/HEAD/evaluation/four_dimensional_metrics.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9f722ab626794328"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}