{"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-chatgpt-on-algorithmic-reasoning","title":"Benchmarking ChatGPT on Algorithmic Reasoning","arxiv_id":"2404.03441","date":"2024-04-04","proceeding":null,"authors":["Sean McLeish","Avi Schwarzschild","Tom Goldstein"],"abstract":"We evaluate ChatGPT's ability to solve algorithm problems from the CLRS benchmark suite that is designed for GNNs. The benchmark requires the use of a specified classical algorithm to solve a given problem. We find that ChatGPT outperforms specialist GNN models, using Python to successfully solve these problems. This raises new points in the discussion about learning algorithms with neural networks and how we think about what out of distribution testing looks like with web scale training data.","url_abs":"https://arxiv.org/abs/2404.03441v2","url_pdf":"https://arxiv.org/pdf/2404.03441v2.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-chatgpt-on-algorithmic-reasoning","repo_url":"https://github.com/mcleish7/clrs4lm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.03441","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03441"}},"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/mcleish7/clrs4lm","reach":null}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":3,"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":0,"samples":[{"code_sha256_prefix":"6cd2d9131bcd89ca","entry":"bubble_sort","repo":"mcleish7/clrs4lm","repo_kind":"official","path":"prompt_generator.py","file_url":"https://github.com/mcleish7/clrs4lm/blob/HEAD/prompt_generator.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6cd2d9131bcd89ca"}},{"code_sha256_prefix":"43f1d0212c68eb43","entry":"heap_sort","repo":"mcleish7/clrs4lm","repo_kind":"official","path":"prompt_generator.py","file_url":"https://github.com/mcleish7/clrs4lm/blob/HEAD/prompt_generator.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"43f1d0212c68eb43"}},{"code_sha256_prefix":"bf060c9cd39fae92","entry":"insertion_sort","repo":"mcleish7/clrs4lm","repo_kind":"official","path":"prompt_generator.py","file_url":"https://github.com/mcleish7/clrs4lm/blob/HEAD/prompt_generator.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bf060c9cd39fae92"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}