{"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/llemma-an-open-language-model-for-mathematics","title":"Llemma: An Open Language Model For Mathematics","arxiv_id":"2310.10631","date":"2023-10-16","proceeding":null,"authors":["Zhangir Azerbayev","Hailey Schoelkopf","Keiran Paster","Marco Dos Santos","Stephen Mcaleer","Albert Q. Jiang","Jia Deng","Stella Biderman","Sean Welleck"],"abstract":"We present Llemma, a large language model for mathematics. We continue pretraining Code Llama on the Proof-Pile-2, a mixture of scientific papers, web data containing mathematics, and mathematical code, yielding Llemma. On the MATH benchmark Llemma outperforms all known open base models, as well as the unreleased Minerva model suite on an equi-parameter basis. Moreover, Llemma is capable of tool use and formal theorem proving without any further finetuning. We openly release all artifacts, including 7 billion and 34 billion parameter models, the Proof-Pile-2, and code to replicate our experiments.","url_abs":"https://arxiv.org/abs/2310.10631v3","url_pdf":"https://arxiv.org/pdf/2310.10631v3.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":"llemma-an-open-language-model-for-mathematics","repo_url":"https://github.com/EleutherAI/math-lm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"llemma-an-open-language-model-for-mathematics","repo_url":"https://github.com/eleutherai/gpt-neox","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"llemma-an-open-language-model-for-mathematics","repo_url":"https://github.com/wellecks/llmstep","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"llemma-an-open-language-model-for-mathematics","repo_url":"https://github.com/wellecks/llemma_formal2formal","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"arithmetic-reasoning","task_name":"Arithmetic Reasoning"},{"task_slug":"automated-theorem-proving","task_name":"Automated Theorem Proving"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"math","task_name":"Math"},{"task_slug":"model","task_name":"model"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/arithmetic-reasoning-on-gsm8k","task":"Arithmetic Reasoning","dataset":"GSM8K","model":"Llemma 34B","rank_in_archive_order":132,"of":164,"metrics":{"Accuracy":"51.5","Parameters (Billion)":"34"},"uses_additional_data":false},{"leaderboard":"/sota/arithmetic-reasoning-on-gsm8k","task":"Arithmetic Reasoning","dataset":"GSM8K","model":"Llemma 7B","rank_in_archive_order":142,"of":164,"metrics":{"Accuracy":"36.4","Parameters (Billion)":"7"},"uses_additional_data":false},{"leaderboard":"/sota/automated-theorem-proving-on-minif2f-test","task":"Automated Theorem Proving","dataset":"miniF2F-test","model":"LLEMMA-7b","rank_in_archive_order":21,"of":29,"metrics":{"ITP":"Lean","Pass@32":"26.2","cumulative":"26.2"},"uses_additional_data":false},{"leaderboard":"/sota/automated-theorem-proving-on-minif2f-test","task":"Automated Theorem Proving","dataset":"miniF2F-test","model":"LLEMMA-34b","rank_in_archive_order":22,"of":29,"metrics":{"ITP":"Lean","Pass@32":"25.8","cumulative":"25.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.10631","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.10631"}},"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/eleutherai/gpt-neox","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wellecks/llemma_formal2formal","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/EleutherAI/math-lm","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wellecks/llmstep","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":6,"repositories":1},"listed":{"samples":1,"ran":0,"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":"404e4e000ce8e5a4","entry":"create_outputs","repo":"EleutherAI/math-lm","repo_kind":"official","path":"proof_pile_2/algebraic_stack/process_isabelle_proofsteps.py","file_url":"https://github.com/EleutherAI/math-lm/blob/HEAD/proof_pile_2/algebraic_stack/process_isabelle_proofsteps.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"404e4e000ce8e5a4"}},{"code_sha256_prefix":"a748289feeef8b50","entry":"extract_theory_file","repo":"EleutherAI/math-lm","repo_kind":"official","path":"proof_pile_2/algebraic_stack/process_isabelle_proofsteps.py","file_url":"https://github.com/EleutherAI/math-lm/blob/HEAD/proof_pile_2/algebraic_stack/process_isabelle_proofsteps.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a748289feeef8b50"}},{"code_sha256_prefix":"dc657f552ea0c7e4","entry":"numerical_density","repo":"EleutherAI/math-lm","repo_kind":"official","path":"proof_pile_2/algebraic_stack/process_stack.py","file_url":"https://github.com/EleutherAI/math-lm/blob/HEAD/proof_pile_2/algebraic_stack/process_stack.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dc657f552ea0c7e4"}},{"code_sha256_prefix":"90d0c5e777c36f13","entry":"r_filter","repo":"EleutherAI/math-lm","repo_kind":"official","path":"proof_pile_2/algebraic_stack/process_stack.py","file_url":"https://github.com/EleutherAI/math-lm/blob/HEAD/proof_pile_2/algebraic_stack/process_stack.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"90d0c5e777c36f13"}},{"code_sha256_prefix":"a3b15e19e090eb8d","entry":"split_list","repo":"EleutherAI/math-lm","repo_kind":"official","path":"proof_pile_2/algebraic_stack/process_isabelle_proofsteps.py","file_url":"https://github.com/EleutherAI/math-lm/blob/HEAD/proof_pile_2/algebraic_stack/process_isabelle_proofsteps.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a3b15e19e090eb8d"}},{"code_sha256_prefix":"6557b371083607b5","entry":"standard_filter","repo":"EleutherAI/math-lm","repo_kind":"official","path":"proof_pile_2/algebraic_stack/process_stack.py","file_url":"https://github.com/EleutherAI/math-lm/blob/HEAD/proof_pile_2/algebraic_stack/process_stack.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6557b371083607b5"}},{"code_sha256_prefix":"f227a3efda0fb0e6","entry":"resume_from","repo":"wellecks/llemma_formal2formal","repo_kind":"listed","path":"proofsearch.py","file_url":"https://github.com/wellecks/llemma_formal2formal/blob/HEAD/proofsearch.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f227a3efda0fb0e6"}},{"code_sha256_prefix":"328e227d602c1b9a","entry":"row_of_name","repo":"EleutherAI/math-lm","repo_kind":"official","path":"proof_pile_2/algebraic_stack/process_lean_proofsteps.py","file_url":"https://github.com/EleutherAI/math-lm/blob/HEAD/proof_pile_2/algebraic_stack/process_lean_proofsteps.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"328e227d602c1b9a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}