{"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/qwen2-5-math-technical-report-toward","title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","arxiv_id":"2409.12122","date":"2024-09-18","proceeding":null,"authors":["An Yang","Beichen Zhang","Binyuan Hui","Bofei Gao","Bowen Yu","Chengpeng Li","Dayiheng Liu","Jianhong Tu","Jingren Zhou","Junyang Lin","Keming Lu","Mingfeng Xue","Runji Lin","Tianyu Liu","Xingzhang Ren","Zhenru Zhang"],"abstract":"In this report, we present a series of math-specific large language models: Qwen2.5-Math and Qwen2.5-Math-Instruct-1.5B/7B/72B. The core innovation of the Qwen2.5 series lies in integrating the philosophy of self-improvement throughout the entire pipeline, from pre-training and post-training to inference: (1) During the pre-training phase, Qwen2-Math-Instruct is utilized to generate large-scale, high-quality mathematical data. (2) In the post-training phase, we develop a reward model (RM) by conducting massive sampling from Qwen2-Math-Instruct. This RM is then applied to the iterative evolution of data in supervised fine-tuning (SFT). With a stronger SFT model, it's possible to iteratively train and update the RM, which in turn guides the next round of SFT data iteration. On the final SFT model, we employ the ultimate RM for reinforcement learning, resulting in the Qwen2.5-Math-Instruct. (3) Furthermore, during the inference stage, the RM is used to guide sampling, optimizing the model's performance. Qwen2.5-Math-Instruct supports both Chinese and English, and possess advanced mathematical reasoning capabilities, including Chain-of-Thought (CoT) and Tool-Integrated Reasoning (TIR). We evaluate our models on 10 mathematics datasets in both English and Chinese, such as GSM8K, MATH, GaoKao, AMC23, and AIME24, covering a range of difficulties from grade school level to math competition problems.","url_abs":"https://arxiv.org/abs/2409.12122v1","url_pdf":"https://arxiv.org/pdf/2409.12122v1.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":[],"tasks":[{"task_slug":"gsm8k","task_name":"GSM8K"},{"task_slug":"math","task_name":"Math"},{"task_slug":"math-word-problem-solving","task_name":"Math Word Problem Solving"},{"task_slug":"mathematical-reasoning","task_name":"Mathematical Reasoning"},{"task_slug":"philosophy","task_name":"Philosophy"}],"methods":[{"method_slug":"sft","method_name":"SFT"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"Qwen2.5-Math-72B-Instruct(TIR,Greedy)","rank_in_archive_order":2,"of":135,"metrics":{"Accuracy":"88.1","Parameters (Billions)":"72"},"uses_additional_data":true},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"Qwen2.5-Math-72B-Instruct(COT,Greedy)","rank_in_archive_order":4,"of":135,"metrics":{"Accuracy":"85.9","Parameters (Billions)":"72"},"uses_additional_data":true},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"Qwen2.5-Math-7B-Instruct(TIR,Greedy)","rank_in_archive_order":5,"of":135,"metrics":{"Accuracy":"85.2","Parameters (Billions)":"7"},"uses_additional_data":true},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"Qwen2.5-Math-7B-Instruct(COT,Greedy)","rank_in_archive_order":8,"of":135,"metrics":{"Accuracy":"83.6","Parameters (Billions)":"7"},"uses_additional_data":true},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"Qwen2.5-Math-1.5B-Instruct(TIR,Greedy)","rank_in_archive_order":9,"of":135,"metrics":{"Accuracy":"79.9","Parameters (Billions)":"1.5"},"uses_additional_data":true},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"Qwen2.5-Math-1.5B-Instruct(COT,Greedy)","rank_in_archive_order":12,"of":135,"metrics":{"Accuracy":"75.8","Parameters (Billions)":"1.5"},"uses_additional_data":true},{"leaderboard":"/sota/mathematical-reasoning-on-amc23","task":"Mathematical Reasoning","dataset":"AMC23","model":"Qwen2.5-Math-7B-instruct","rank_in_archive_order":3,"of":3,"metrics":{"Acc":"62.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2409.12122","atlas_url":"https://app.syntology.ai/?focus=2409.12122","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":"2409.12122"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2409.12122\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2409.12122"},"call":"get_concepts_for_paper(arxiv_id=\"2409.12122\")"}],"by_repo":[],"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":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"0cef41a40aaa59dda211684eb2c853e921b43276f14daccf729d2306c8f75b3d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}