{"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/mm-iq-benchmarking-human-like-abstraction-and-1","title":"MM-IQ: Benchmarking Human-Like Abstraction and Reasoning in Multimodal Models","arxiv_id":"2502.00698","date":"2025-02-02","proceeding":null,"authors":["Huanqia Cai","Yijun Yang","Winston Hu"],"abstract":"IQ testing has served as a foundational methodology for evaluating human cognitive capabilities, deliberately decoupling assessment from linguistic background, language proficiency, or domain-specific knowledge to isolate core competencies in abstraction and reasoning. Yet, artificial intelligence research currently lacks systematic benchmarks to quantify these critical cognitive dimensions in multimodal systems. To address this critical gap, we propose MM-IQ, a comprehensive evaluation framework comprising 2,710 meticulously curated test items spanning 8 distinct reasoning paradigms. Through systematic evaluation of leading open-source and proprietary multimodal models, our benchmark reveals striking limitations: even state-of-the-art architectures achieve only marginally superior performance to random chance (27.49% vs. 25% baseline accuracy). This substantial performance chasm highlights the inadequacy of current multimodal systems in approximating fundamental human reasoning capacities, underscoring the need for paradigm-shifting advancements to bridge this cognitive divide.","url_abs":"https://arxiv.org/abs/2502.00698v1","url_pdf":"https://arxiv.org/pdf/2502.00698v1.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":"mm-iq-benchmarking-human-like-abstraction-and-1","repo_url":"https://github.com/AceCHQ/MMIQ","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2502.00698","atlas_url":"https://app.syntology.ai/?focus=2502.00698","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.00698"}},"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/AceCHQ/MMIQ","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":5,"unverified":4},"by_repo_kind":{"official":{"samples":9,"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":0,"samples":[{"code_sha256_prefix":"98c18be2c0a33db2","entry":"extract_choice","repo":"AceCHQ/MMIQ","repo_kind":"official","path":"mmiq/utils/eval_utils.py","file_url":"https://github.com/AceCHQ/MMIQ/blob/HEAD/mmiq/utils/eval_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"98c18be2c0a33db2"}},{"code_sha256_prefix":"e4e30d1813045cfb","entry":"llava_image_processor","repo":"AceCHQ/MMIQ","repo_kind":"official","path":"mmiq/utils/model_utils.py","file_url":"https://github.com/AceCHQ/MMIQ/blob/HEAD/mmiq/utils/model_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e4e30d1813045cfb"}},{"code_sha256_prefix":"c2cf50db9a54f717","entry":"parse_multi_choice_response","repo":"AceCHQ/MMIQ","repo_kind":"official","path":"mmiq/utils/eval_utils.py","file_url":"https://github.com/AceCHQ/MMIQ/blob/HEAD/mmiq/utils/eval_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c2cf50db9a54f717"}},{"code_sha256_prefix":"09fe27c6ee70aa9b","entry":"process_single_sample","repo":"AceCHQ/MMIQ","repo_kind":"official","path":"mmiq/utils/data_utils.py","file_url":"https://github.com/AceCHQ/MMIQ/blob/HEAD/mmiq/utils/data_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"09fe27c6ee70aa9b"}},{"code_sha256_prefix":"fdb3e1f2061eee8e","entry":"run_model","repo":"AceCHQ/MMIQ","repo_kind":"official","path":"mmiq/run_llava.py","file_url":"https://github.com/AceCHQ/MMIQ/blob/HEAD/mmiq/run_llava.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fdb3e1f2061eee8e"}},{"code_sha256_prefix":"7712b2cda4dfffde","entry":"call_llava_engine_df","repo":"AceCHQ/MMIQ","repo_kind":"official","path":"mmiq/utils/model_utils.py","file_url":"https://github.com/AceCHQ/MMIQ/blob/HEAD/mmiq/utils/model_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7712b2cda4dfffde"}},{"code_sha256_prefix":"81305e2c0d5ef1a9","entry":"check_is_number","repo":"AceCHQ/MMIQ","repo_kind":"official","path":"mmiq/utils/eval_utils.py","file_url":"https://github.com/AceCHQ/MMIQ/blob/HEAD/mmiq/utils/eval_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"81305e2c0d5ef1a9"}},{"code_sha256_prefix":"ce93b7e192e1a8b7","entry":"load_yaml","repo":"AceCHQ/MMIQ","repo_kind":"official","path":"mmiq/utils/data_utils.py","file_url":"https://github.com/AceCHQ/MMIQ/blob/HEAD/mmiq/utils/data_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ce93b7e192e1a8b7"}},{"code_sha256_prefix":"de4427887bed9253","entry":"parse_img_path","repo":"AceCHQ/MMIQ","repo_kind":"official","path":"mmiq/utils/data_utils.py","file_url":"https://github.com/AceCHQ/MMIQ/blob/HEAD/mmiq/utils/data_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"de4427887bed9253"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}