{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/solving-quantitative-reasoning-problems-with","title":"Solving Quantitative Reasoning Problems with Language Models","arxiv_id":"2206.14858","date":"2022-06-29","proceeding":null,"authors":["Aitor Lewkowycz","Anders Andreassen","David Dohan","Ethan Dyer","Henryk Michalewski","Vinay Ramasesh","Ambrose Slone","Cem Anil","Imanol Schlag","Theo Gutman-Solo","Yuhuai Wu","Behnam Neyshabur","Guy Gur-Ari","Vedant Misra"],"abstract":"Language models have achieved remarkable performance on a wide range of tasks that require natural language understanding. Nevertheless, state-of-the-art models have generally struggled with tasks that require quantitative reasoning, such as solving mathematics, science, and engineering problems at the college level. To help close this gap, we introduce Minerva, a large language model pretrained on general natural language data and further trained on technical content. The model achieves state-of-the-art performance on technical benchmarks without the use of external tools. We also evaluate our model on over two hundred undergraduate-level problems in physics, biology, chemistry, economics, and other sciences that require quantitative reasoning, and find that the model can correctly answer nearly a third of them.","url_abs":"https://arxiv.org/abs/2206.14858v2","url_pdf":"https://arxiv.org/pdf/2206.14858v2.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":"solving-quantitative-reasoning-problems-with","repo_url":"https://github.com/gair-nlp/abel","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"arithmetic-reasoning","task_name":"Arithmetic Reasoning"},{"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-word-problem-solving","task_name":"Math Word Problem Solving"},{"task_slug":"multi-task-language-understanding","task_name":"Multi-task Language Understanding"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"}],"methods":[{"method_slug":"1-bit-adam","method_name":"1-bit Adam"},{"method_slug":"adam","method_name":"Adam"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/arithmetic-reasoning-on-gsm8k","task":"Arithmetic Reasoning","dataset":"GSM8K","model":"Minerva 62B (maj5@100)","rank_in_archive_order":26,"of":164,"metrics":{"Accuracy":"89","Parameters (Billion)":"62"},"uses_additional_data":false},{"leaderboard":"/sota/arithmetic-reasoning-on-gsm8k","task":"Arithmetic Reasoning","dataset":"GSM8K","model":"Minerva 540B (CoT)","rank_in_archive_order":77,"of":164,"metrics":{"Accuracy":"78.5","Parameters (Billion)":"540"},"uses_additional_data":false},{"leaderboard":"/sota/arithmetic-reasoning-on-gsm8k","task":"Arithmetic Reasoning","dataset":"GSM8K","model":"Minerva 62B (maj1@100)","rank_in_archive_order":105,"of":164,"metrics":{"Accuracy":"68.5","Parameters (Billion)":"62"},"uses_additional_data":true},{"leaderboard":"/sota/arithmetic-reasoning-on-gsm8k","task":"Arithmetic Reasoning","dataset":"GSM8K","model":"Minerva 8B (maj5@100)","rank_in_archive_order":122,"of":164,"metrics":{"Accuracy":"56.8","Parameters (Billion)":"8"},"uses_additional_data":false},{"leaderboard":"/sota/arithmetic-reasoning-on-gsm8k","task":"Arithmetic Reasoning","dataset":"GSM8K","model":"PaLM 540B (8-shot)","rank_in_archive_order":124,"of":164,"metrics":{"Accuracy":"56.5","Parameters (Billion)":"540"},"uses_additional_data":true},{"leaderboard":"/sota/arithmetic-reasoning-on-gsm8k","task":"Arithmetic Reasoning","dataset":"GSM8K","model":"Minerva 62B (8-shot)","rank_in_archive_order":130,"of":164,"metrics":{"Accuracy":" 52.4","Parameters (Billion)":"62"},"uses_additional_data":true},{"leaderboard":"/sota/arithmetic-reasoning-on-gsm8k","task":"Arithmetic Reasoning","dataset":"GSM8K","model":"PaLM 62B (8-shot)","rank_in_archive_order":145,"of":164,"metrics":{"Accuracy":"33.0","Parameters (Billion)":"62"},"uses_additional_data":true},{"leaderboard":"/sota/arithmetic-reasoning-on-gsm8k","task":"Arithmetic Reasoning","dataset":"GSM8K","model":"Minerva 8B-maj1@k (8-shot)","rank_in_archive_order":148,"of":164,"metrics":{"Accuracy":" 28.4","Parameters (Billion)":"8"},"uses_additional_data":true},{"leaderboard":"/sota/arithmetic-reasoning-on-gsm8k","task":"Arithmetic Reasoning","dataset":"GSM8K","model":"Minerva 8B (8-shot)","rank_in_archive_order":157,"of":164,"metrics":{"Accuracy":"16.2","Parameters (Billion)":"8"},"uses_additional_data":true},{"leaderboard":"/sota/arithmetic-reasoning-on-gsm8k","task":"Arithmetic Reasoning","dataset":"GSM8K","model":"PaLM 8B (8-shot)","rank_in_archive_order":163,"of":164,"metrics":{"Accuracy":"4.1","Parameters (Billion)":"8"},"uses_additional_data":true},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"Minerva 62B (maj5@256)","rank_in_archive_order":21,"of":135,"metrics":{"Accuracy":"64.9","Parameters (Billions)":"62"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"Minerva 540B (maj1@k, k=64)","rank_in_archive_order":48,"of":135,"metrics":{"Accuracy":"50.3"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"Minerva 8B (maj5@256)","rank_in_archive_order":57,"of":135,"metrics":{"Accuracy":"47.6","Parameters (Billions)":"8"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"Minerva 62B (maj1@k, k=64)","rank_in_archive_order":73,"of":135,"metrics":{"Accuracy":"43.4","Parameters (Billions)":"62"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"Minerva 540B","rank_in_archive_order":82,"of":135,"metrics":{"Accuracy":"33.6","Parameters (Billions)":"540"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"Minerva 62B (4-shot)","rank_in_archive_order":94,"of":135,"metrics":{"Accuracy":"27.6","Parameters (Billions)":"62"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"Minerva 8B (maj1@k, k=64)","rank_in_archive_order":97,"of":135,"metrics":{"Accuracy":"25.4","Parameters (Billions)":"8"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"davinci-002 175B","rank_in_archive_order":105,"of":135,"metrics":{"Accuracy":"19.1","Parameters (Billions)":"175"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"Minerva 8B","rank_in_archive_order":109,"of":135,"metrics":{"Accuracy":"14.1","Parameters (Billions)":"8"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"PaLM 540B","rank_in_archive_order":117,"of":135,"metrics":{"Accuracy":"8.8","Parameters (Billions)":"540"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"PaLM 8B (fine-tuned)","rank_in_archive_order":126,"of":135,"metrics":{"Accuracy":"5.6","Parameters (Billions)":"8"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"PaLM 62B","rank_in_archive_order":130,"of":135,"metrics":{"Accuracy":"4.4","Parameters (Billions)":"62"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"PaLM 8B","rank_in_archive_order":135,"of":135,"metrics":{"Accuracy":"1.5","Parameters (Billions)":"8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2206.14858","atlas_url":"https://app.syntology.ai/?focus=2206.14858","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2206.14858"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2206.14858\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2206.14858"},"call":"get_concepts_for_paper(arxiv_id=\"2206.14858\")"}],"by_repo":[{"repo":"gair-nlp/abel","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"8adf806df6e906a5ddacfa9c4571347ad041e681d330e2f57a2a122ea557a9ce","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}