{"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/mapeval-a-map-based-evaluation-of-geo-spatial","title":"MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation Models","arxiv_id":"2501.00316","date":"2024-12-31","proceeding":null,"authors":["Mahir Labib Dihan","Md Tanvir Hassan","Md Tanvir Parvez","Md Hasebul Hasan","Md Almash Alam","Muhammad Aamir Cheema","Mohammed Eunus Ali","Md Rizwan Parvez"],"abstract":"Recent advancements in foundation models have enhanced AI systems' capabilities in autonomous tool usage and reasoning. However, their ability in location or map-based reasoning - which improves daily life by optimizing navigation, facilitating resource discovery, and streamlining logistics - has not been systematically studied. To bridge this gap, we introduce MapEval, a benchmark designed to assess diverse and complex map-based user queries with geo-spatial reasoning. MapEval features three task types (textual, API-based, and visual) that require collecting world information via map tools, processing heterogeneous geo-spatial contexts (e.g., named entities, travel distances, user reviews or ratings, images), and compositional reasoning, which all state-of-the-art foundation models find challenging. Comprising 700 unique multiple-choice questions about locations across 180 cities and 54 countries, MapEval evaluates foundation models' ability to handle spatial relationships, map infographics, travel planning, and navigation challenges. Using MapEval, we conducted a comprehensive evaluation of 28 prominent foundation models. While no single model excelled across all tasks, Claude-3.5-Sonnet, GPT-4o, and Gemini-1.5-Pro achieved competitive performance overall. However, substantial performance gaps emerged, particularly in MapEval, where agents with Claude-3.5-Sonnet outperformed GPT-4o and Gemini-1.5-Pro by 16% and 21%, respectively, and the gaps became even more amplified when compared to open-source LLMs. Our detailed analyses provide insights into the strengths and weaknesses of current models, though all models still fall short of human performance by more than 20% on average, struggling with complex map images and rigorous geo-spatial reasoning. This gap highlights MapEval's critical role in advancing general-purpose foundation models with stronger geo-spatial understanding.","url_abs":"https://arxiv.org/abs/2501.00316v1","url_pdf":"https://arxiv.org/pdf/2501.00316v1.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":"mapeval-a-map-based-evaluation-of-geo-spatial","repo_url":"https://github.com/MapEval/MapEval-API","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"mapeval-a-map-based-evaluation-of-geo-spatial","repo_url":"https://github.com/MapEval/MapEval-Textual","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"mapeval-a-map-based-evaluation-of-geo-spatial","repo_url":"https://github.com/MapEval/MapEval-Visual","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"multiple-choice","task_name":"Multiple-choice"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"spatial-reasoning","task_name":"Spatial Reasoning"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"}],"methods":[{"method_slug":null,"method_name":"Travel"}],"datasets_introduced":[{"slug":"mapeval","name":"MapEval","full_name":""},{"slug":"mapeval-api","name":"MapEval-API","full_name":""},{"slug":"mapeval-textual","name":"MapEval-Textual","full_name":""},{"slug":"mapeval-visual","name":"MapEval-Visual","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-mapeval-api-1","task":"Question Answering","dataset":"MapEval-API","model":"Claude-3.5-Sonnet (ReAct)","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy (%)":"64.00"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-mapeval-api-1","task":"Question Answering","dataset":"MapEval-API","model":"GPT-3.5-Turbo (Chameleon)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy (%)":"49.33"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-mapeval-textual","task":"Question Answering","dataset":"MapEval-Textual","model":"Claude-3.5-Sonnet","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy (% )":"66.33"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-mapeval-visual","task":"Visual Question Answering","dataset":"MapEval-Visual","model":"Claude-3.5-Sonnet","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy (% )":"61.65"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2501.00316","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.00316"}},"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/MapEval/MapEval-Textual","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MapEval/MapEval-API","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MapEval/MapEval-Visual","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":2}},"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":3,"samples":[{"code_sha256_prefix":"2147a122d4d10e30","entry":"extract","repo":"MapEval/MapEval-Textual","repo_kind":"official","path":"Evaluator.py","file_url":"https://github.com/MapEval/MapEval-Textual/blob/HEAD/Evaluator.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2147a122d4d10e30"}},{"code_sha256_prefix":"402a187397a37a7c","entry":"extract_response","repo":"MapEval/MapEval-Visual","repo_kind":"official","path":"evaluation.py","file_url":"https://github.com/MapEval/MapEval-Visual/blob/HEAD/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"402a187397a37a7c"}},{"code_sha256_prefix":"ef55fde2911f41f3","entry":"search_evaluation_by_model","repo":"MapEval/MapEval-Textual","repo_kind":"official","path":"Evaluator.py","file_url":"https://github.com/MapEval/MapEval-Textual/blob/HEAD/Evaluator.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":"ef55fde2911f41f3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}