{"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":"/sota/math-word-problem-solving-on-math","task":{"name":"Math Word Problem Solving","url":"/task/math-word-problem-solving","note":null},"dataset":{"name":"MATH","url":"/dataset/math"},"category":"Reasoning","categories":["Reasoning"],"category_note":null,"description":"A math word problem is a mathematical exercise (such as in a textbook, worksheet, or exam) where significant background information on the problem is presented in ordinary language rather than in mathematical notation. As most word problems involve a narrative of some sort, they are sometimes referred to as story problems and may vary in the amount of technical language used.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Accuracy","Parameters (Billions)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction; the tokens 'score' and 'time' are not used on this page); null = not inferred, chart draws points only","by_metric":{"Accuracy":"higher","Parameters (Billions)":null}},"counts":{"rows":135,"rows_with_code":121,"rows_with_paper_page":132,"rows_dated":132,"rows_using_additional_data":70},"rows":[{"rank_in_archive_order":1,"model":"Gemini 2.0 Flash Experimental","metrics":{"Accuracy":"89.7"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":2,"model":"Qwen2.5-Math-72B-Instruct(TIR,Greedy)","metrics":{"Accuracy":"88.1","Parameters (Billions)":"72"},"uses_additional_data":true,"paper_date":"2024-09-18","paper":"/paper/qwen2-5-math-technical-report-toward","paper_url":"https://arxiv.org/abs/2409.12122v1","paper_title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":3,"model":"GPT-4 Turbo (MACM, w/code, voting)","metrics":{"Accuracy":"87.920"},"uses_additional_data":false,"paper_date":"2024-04-06","paper":"/paper/macm-utilizing-a-multi-agent-system-for","paper_url":"https://arxiv.org/abs/2404.04735v2","paper_title":"MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems","code":"https://github.com/bin123apple/macm","n_code_links":1,"official":{"repos":["bin123apple/macm"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":1,"sample_list":"/paper/macm-utilizing-a-multi-agent-system-for#ran","syntology_url":"https://syntology.ai/paper/2404.04735","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.04735"}}}},{"rank_in_archive_order":4,"model":"Qwen2.5-Math-72B-Instruct(COT,Greedy)","metrics":{"Accuracy":"85.9","Parameters (Billions)":"72"},"uses_additional_data":true,"paper_date":"2024-09-18","paper":"/paper/qwen2-5-math-technical-report-toward","paper_url":"https://arxiv.org/abs/2409.12122v1","paper_title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":5,"model":"Qwen2.5-Math-7B-Instruct(TIR,Greedy)","metrics":{"Accuracy":"85.2","Parameters (Billions)":"7"},"uses_additional_data":true,"paper_date":"2024-09-18","paper":"/paper/qwen2-5-math-technical-report-toward","paper_url":"https://arxiv.org/abs/2409.12122v1","paper_title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":6,"model":"GPT-4-code model (CSV, w/ code, SC, k=16)","metrics":{"Accuracy":"84.3"},"uses_additional_data":false,"paper_date":"2023-08-15","paper":"/paper/solving-challenging-math-word-problems-using","paper_url":"https://arxiv.org/abs/2308.07921v1","paper_title":"Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification","code":"https://github.com/kipok/nemo-skills","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":7,"model":"Qwen2-Math-72B-Instruct(greedy)","metrics":{"Accuracy":"84.0","Parameters (Billions)":"72"},"uses_additional_data":true,"paper_date":"2024-07-15","paper":"/paper/qwen2-technical-report","paper_url":"https://arxiv.org/abs/2407.10671v4","paper_title":"Qwen2 Technical Report","code":"https://github.com/qwenlm/qwen1.5","n_code_links":6,"official":null,"syntology":null},{"rank_in_archive_order":8,"model":"Qwen2.5-Math-7B-Instruct(COT,Greedy)","metrics":{"Accuracy":"83.6","Parameters (Billions)":"7"},"uses_additional_data":true,"paper_date":"2024-09-18","paper":"/paper/qwen2-5-math-technical-report-toward","paper_url":"https://arxiv.org/abs/2409.12122v1","paper_title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":9,"model":"Qwen2.5-Math-1.5B-Instruct(TIR,Greedy)","metrics":{"Accuracy":"79.9","Parameters (Billions)":"1.5"},"uses_additional_data":true,"paper_date":"2024-09-18","paper":"/paper/qwen2-5-math-technical-report-toward","paper_url":"https://arxiv.org/abs/2409.12122v1","paper_title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":10,"model":"OpenMath2-Llama3.1-70B (majority@256)","metrics":{"Accuracy":"79.6"},"uses_additional_data":true,"paper_date":"2024-10-02","paper":"/paper/openmathinstruct-2-accelerating-ai-for-math","paper_url":"https://arxiv.org/abs/2410.01560v2","paper_title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","code":"https://github.com/NVIDIA/NeMo-Skills","n_code_links":1,"official":null,"syntology":{"n_ran":12,"n_constructed":0,"n_ran_checked":5,"n_instrument":7,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/openmathinstruct-2-accelerating-ai-for-math#ran","syntology_url":"https://syntology.ai/paper/2410.01560","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01560"}}}},{"rank_in_archive_order":11,"model":"OpenMath2-Llama3.1-8B (majority@256)","metrics":{"Accuracy":"76.1"},"uses_additional_data":true,"paper_date":"2024-10-02","paper":"/paper/openmathinstruct-2-accelerating-ai-for-math","paper_url":"https://arxiv.org/abs/2410.01560v2","paper_title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","code":"https://github.com/NVIDIA/NeMo-Skills","n_code_links":1,"official":null,"syntology":{"n_ran":12,"n_constructed":0,"n_ran_checked":5,"n_instrument":7,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/openmathinstruct-2-accelerating-ai-for-math#ran","syntology_url":"https://syntology.ai/paper/2410.01560","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01560"}}}},{"rank_in_archive_order":12,"model":"Qwen2.5-Math-1.5B-Instruct(COT,Greedy)","metrics":{"Accuracy":"75.8","Parameters (Billions)":"1.5"},"uses_additional_data":true,"paper_date":"2024-09-18","paper":"/paper/qwen2-5-math-technical-report-toward","paper_url":"https://arxiv.org/abs/2409.12122v1","paper_title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":13,"model":"GPT-4-code model (CSV, w/ code)","metrics":{"Accuracy":"73.5"},"uses_additional_data":false,"paper_date":"2023-08-15","paper":"/paper/solving-challenging-math-word-problems-using","paper_url":"https://arxiv.org/abs/2308.07921v1","paper_title":"Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification","code":"https://github.com/kipok/nemo-skills","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":14,"model":"CR (GPT-4-turbo model, w/ code)","metrics":{"Accuracy":"72.2"},"uses_additional_data":false,"paper_date":"2023-08-08","paper":"/paper/cumulative-reasoning-with-large-language","paper_url":"https://arxiv.org/abs/2308.04371v6","paper_title":"Cumulative Reasoning with Large Language Models","code":"https://github.com/iiis-ai/cumulative-reasoning","n_code_links":1,"official":{"repos":["iiis-ai/cumulative-reasoning"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_samples":6,"n_pointer_only_licence":6,"sample_list":"/paper/cumulative-reasoning-with-large-language#ran","syntology_url":"https://syntology.ai/paper/2308.04371","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.04371"}}}},{"rank_in_archive_order":15,"model":"OpenMath2-Llama3.1-70B","metrics":{"Accuracy":"71.9"},"uses_additional_data":true,"paper_date":"2024-10-02","paper":"/paper/openmathinstruct-2-accelerating-ai-for-math","paper_url":"https://arxiv.org/abs/2410.01560v2","paper_title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","code":"https://github.com/NVIDIA/NeMo-Skills","n_code_links":1,"official":null,"syntology":{"n_ran":12,"n_constructed":0,"n_ran_checked":5,"n_instrument":7,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/openmathinstruct-2-accelerating-ai-for-math#ran","syntology_url":"https://syntology.ai/paper/2410.01560","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01560"}}}},{"rank_in_archive_order":16,"model":"LogicNet (with code interpreter)","metrics":{"Accuracy":"71.2"},"uses_additional_data":true,"paper_date":"2023-08-15","paper":"/paper/solving-challenging-math-word-problems-using","paper_url":"https://arxiv.org/abs/2308.07921v1","paper_title":"Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification","code":"https://github.com/kipok/nemo-skills","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":17,"model":"Qwen2-72B-Instruct-Step-DPO (0-shot CoT, w/o code)","metrics":{"Accuracy":"70.8"},"uses_additional_data":true,"paper_date":"2024-06-26","paper":"/paper/step-dpo-step-wise-preference-optimization","paper_url":"https://arxiv.org/abs/2406.18629v1","paper_title":"Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs","code":"https://github.com/dvlab-research/step-dpo","n_code_links":1,"official":{"repos":["dvlab-research/step-dpo"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":1,"n_samples":12,"n_pointer_only_licence":12,"sample_list":"/paper/step-dpo-step-wise-preference-optimization#ran","syntology_url":"https://syntology.ai/paper/2406.18629","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18629"}}}},{"rank_in_archive_order":18,"model":"GPT-4-code model (w/ code)","metrics":{"Accuracy":"69.7"},"uses_additional_data":false,"paper_date":"2023-08-15","paper":"/paper/solving-challenging-math-word-problems-using","paper_url":"https://arxiv.org/abs/2308.07921v1","paper_title":"Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification","code":"https://github.com/kipok/nemo-skills","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":19,"model":"OpenMath2-Llama3.1-8B","metrics":{"Accuracy":"67.8"},"uses_additional_data":true,"paper_date":"2024-10-02","paper":"/paper/openmathinstruct-2-accelerating-ai-for-math","paper_url":"https://arxiv.org/abs/2410.01560v2","paper_title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","code":"https://github.com/NVIDIA/NeMo-Skills","n_code_links":1,"official":null,"syntology":{"n_ran":12,"n_constructed":0,"n_ran_checked":5,"n_instrument":7,"n_unverified":3,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/openmathinstruct-2-accelerating-ai-for-math#ran","syntology_url":"https://syntology.ai/paper/2410.01560","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01560"}}}},{"rank_in_archive_order":20,"model":"AlphaMath-7B-SBS@3","metrics":{"Accuracy":"66.3"},"uses_additional_data":false,"paper_date":"2024-05-06","paper":"/paper/alphamath-almost-zero-process-supervision","paper_url":"https://arxiv.org/abs/2405.03553v3","paper_title":"AlphaMath Almost Zero: Process Supervision without Process","code":"https://github.com/MARIO-Math-Reasoning/Super_MARIO","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":21,"model":"Minerva 62B (maj5@256)","metrics":{"Accuracy":"64.9","Parameters (Billions)":"62"},"uses_additional_data":false,"paper_date":"2022-06-29","paper":"/paper/solving-quantitative-reasoning-problems-with","paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","code":"https://github.com/gair-nlp/abel","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":22,"model":"DAMOMath-7B","metrics":{"Accuracy":"64.5","Parameters (Billions)":"7"},"uses_additional_data":true,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":23,"model":"MMOS-DeepSeekMath-7B(0-shot,k=50)","metrics":{"Accuracy":"63.7","Parameters (Billions)":"7"},"uses_additional_data":true,"paper_date":"2024-02-23","paper":"/paper/an-empirical-study-of-data-ability-boundary","paper_url":"https://arxiv.org/abs/2403.00799v1","paper_title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","code":"https://github.com/cyzhh/MMOS","n_code_links":1,"official":{"repos":["cyzhh/MMOS"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":2,"n_samples":11,"n_pointer_only_licence":11,"sample_list":"/paper/an-empirical-study-of-data-ability-boundary#ran","syntology_url":"https://syntology.ai/paper/2403.00799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00799"}}}},{"rank_in_archive_order":24,"model":"GPT-4-code model (w/o code)","metrics":{"Accuracy":"60.8"},"uses_additional_data":false,"paper_date":"2023-08-15","paper":"/paper/solving-challenging-math-word-problems-using","paper_url":"https://arxiv.org/abs/2308.07921v1","paper_title":"Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification","code":"https://github.com/kipok/nemo-skills","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":25,"model":"OpenMath-CodeLlama-70B (w/ code, SC, k=50)","metrics":{"Accuracy":"60.4","Parameters (Billions)":"70"},"uses_additional_data":true,"paper_date":"2024-02-15","paper":"/paper/openmathinstruct-1-a-1-8-million-math","paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","code":"https://github.com/kipok/nemo-skills","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":26,"model":"OpenMath-CodeLlama-34B (w/ code, SC, k=50)","metrics":{"Accuracy":"60.2","Parameters (Billions)":"34"},"uses_additional_data":true,"paper_date":"2024-02-15","paper":"/paper/openmathinstruct-1-a-1-8-million-math","paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","code":"https://github.com/kipok/nemo-skills","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":27,"model":"ToRA-Code 34B model (w/ code, SC, k=50)","metrics":{"Accuracy":"60.0","Parameters (Billions)":"34"},"uses_additional_data":true,"paper_date":"2023-09-29","paper":"/paper/tora-a-tool-integrated-reasoning-agent-for","paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","code":"https://github.com/microsoft/tora","n_code_links":1,"official":{"repos":["microsoft/tora"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":1,"n_samples":12,"n_pointer_only_licence":9,"sample_list":"/paper/tora-a-tool-integrated-reasoning-agent-for#ran","syntology_url":"https://syntology.ai/paper/2309.17452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17452"}}}},{"rank_in_archive_order":28,"model":"DeepSeekMATH-RL-7B (w/ code, greedy decoding)","metrics":{"Accuracy":"58.8","Parameters (Billions)":"7"},"uses_additional_data":true,"paper_date":"2024-02-05","paper":"/paper/deepseekmath-pushing-the-limits-of","paper_url":"https://arxiv.org/abs/2402.03300v3","paper_title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","code":"https://github.com/shibing624/medicalgpt","n_code_links":5,"official":{"repos":["deepseek-ai/deepseek-math"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":14,"n_constructed":0,"n_ran_checked":3,"n_instrument":11,"n_unverified":10,"n_samples":24,"n_pointer_only_licence":3,"sample_list":"/paper/deepseekmath-pushing-the-limits-of#ran","syntology_url":"https://syntology.ai/paper/2402.03300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03300"}}}},{"rank_in_archive_order":29,"model":"OpenMath-Llama2-70B (w/ code, SC, k=50)","metrics":{"Accuracy":"58.3","Parameters (Billions)":"70"},"uses_additional_data":true,"paper_date":"2024-02-15","paper":"/paper/openmathinstruct-1-a-1-8-million-math","paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","code":"https://github.com/kipok/nemo-skills","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":30,"model":"CR (GPT-4 model, w/o code)","metrics":{"Accuracy":"58.0"},"uses_additional_data":false,"paper_date":"2023-08-08","paper":"/paper/cumulative-reasoning-with-large-language","paper_url":"https://arxiv.org/abs/2308.04371v6","paper_title":"Cumulative Reasoning with Large Language Models","code":"https://github.com/iiis-ai/cumulative-reasoning","n_code_links":1,"official":{"repos":["iiis-ai/cumulative-reasoning"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_samples":6,"n_pointer_only_licence":6,"sample_list":"/paper/cumulative-reasoning-with-large-language#ran","syntology_url":"https://syntology.ai/paper/2308.04371","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.04371"}}}},{"rank_in_archive_order":31,"model":"OpenMath-CodeLlama-13B (w/ code, SC, k=50)","metrics":{"Accuracy":"57.6","Parameters (Billions)":"13"},"uses_additional_data":true,"paper_date":"2024-02-15","paper":"/paper/openmathinstruct-1-a-1-8-million-math","paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","code":"https://github.com/kipok/nemo-skills","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":32,"model":"OpenMath-Mistral-7B (w/ code, SC, k=50)","metrics":{"Accuracy":"57.2","Parameters (Billions)":"7"},"uses_additional_data":true,"paper_date":"2024-02-15","paper":"/paper/openmathinstruct-1-a-1-8-million-math","paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","code":"https://github.com/kipok/nemo-skills","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":33,"model":"ToRA 70B (w/ code, SC, k=50)","metrics":{"Accuracy":"56.9","Parameters (Billions)":"70"},"uses_additional_data":true,"paper_date":"2023-09-29","paper":"/paper/tora-a-tool-integrated-reasoning-agent-for","paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","code":"https://github.com/microsoft/tora","n_code_links":1,"official":{"repos":["microsoft/tora"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":1,"n_samples":12,"n_pointer_only_licence":9,"sample_list":"/paper/tora-a-tool-integrated-reasoning-agent-for#ran","syntology_url":"https://syntology.ai/paper/2309.17452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17452"}}}},{"rank_in_archive_order":34,"model":"SKiC (GPT-4 model)","metrics":{"Accuracy":"56.4"},"uses_additional_data":false,"paper_date":"2023-08-01","paper":"/paper/skills-in-context-prompting-unlocking","paper_url":"https://arxiv.org/abs/2308.00304v3","paper_title":"Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":35,"model":"DART-Math-Llama3-70B-Prop2Diff (0-shot CoT, w/o code)","metrics":{"Accuracy":"56.1","Parameters (Billions)":"70"},"uses_additional_data":true,"paper_date":"2024-06-18","paper":"/paper/dart-math-difficulty-aware-rejection-tuning-1","paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","code":"https://github.com/hkust-nlp/dart-math","n_code_links":1,"official":{"repos":["hkust-nlp/dart-math"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":2,"n_instrument":8,"n_unverified":2,"n_samples":12,"n_pointer_only_licence":0,"sample_list":"/paper/dart-math-difficulty-aware-rejection-tuning-1#ran","syntology_url":"https://syntology.ai/paper/2407.13690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.13690"}}}},{"rank_in_archive_order":36,"model":"OpenMath-CodeLlama-7B (w/ code, SC, k=50)","metrics":{"Accuracy":"55.6","Parameters (Billions)":"7"},"uses_additional_data":true,"paper_date":"2024-02-15","paper":"/paper/openmathinstruct-1-a-1-8-million-math","paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","code":"https://github.com/kipok/nemo-skills","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":37,"model":"MMOS-DeepSeekMath-7B(0-shot)","metrics":{"Accuracy":"55.0","Parameters (Billions)":"7"},"uses_additional_data":true,"paper_date":"2024-02-23","paper":"/paper/an-empirical-study-of-data-ability-boundary","paper_url":"https://arxiv.org/abs/2403.00799v1","paper_title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","code":"https://github.com/cyzhh/MMOS","n_code_links":1,"official":{"repos":["cyzhh/MMOS"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":2,"n_samples":11,"n_pointer_only_licence":11,"sample_list":"/paper/an-empirical-study-of-data-ability-boundary#ran","syntology_url":"https://syntology.ai/paper/2403.00799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00799"}}}},{"rank_in_archive_order":38,"model":"DART-Math-Llama3-70B-Uniform (0-shot CoT, w/o code)","metrics":{"Accuracy":"54.9","Parameters (Billions)":"70"},"uses_additional_data":true,"paper_date":"2024-06-18","paper":"/paper/dart-math-difficulty-aware-rejection-tuning-1","paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","code":"https://github.com/hkust-nlp/dart-math","n_code_links":1,"official":{"repos":["hkust-nlp/dart-math"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":2,"n_instrument":8,"n_unverified":2,"n_samples":12,"n_pointer_only_licence":0,"sample_list":"/paper/dart-math-difficulty-aware-rejection-tuning-1#ran","syntology_url":"https://syntology.ai/paper/2407.13690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.13690"}}}},{"rank_in_archive_order":39,"model":"PHP (GPT-4 model)","metrics":{"Accuracy":"53.9"},"uses_additional_data":false,"paper_date":"2023-04-19","paper":"/paper/progressive-hint-prompting-improves-reasoning","paper_url":"https://arxiv.org/abs/2304.09797v6","paper_title":"Progressive-Hint Prompting Improves Reasoning in Large Language Models","code":"https://github.com/chuanyang-Zheng/Progressive-Hint","n_code_links":1,"official":{"repos":["chuanyang-Zheng/Progressive-Hint"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":4,"sample_list":"/paper/progressive-hint-prompting-improves-reasoning#ran","syntology_url":"https://syntology.ai/paper/2304.09797","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.09797"}}}},{"rank_in_archive_order":40,"model":"DART-Math-DSMath-7B-Prop2Diff (0-shot CoT, w/o code)","metrics":{"Accuracy":"53.6","Parameters (Billions)":"7"},"uses_additional_data":true,"paper_date":"2024-06-18","paper":"/paper/dart-math-difficulty-aware-rejection-tuning-1","paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","code":"https://github.com/hkust-nlp/dart-math","n_code_links":1,"official":{"repos":["hkust-nlp/dart-math"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":2,"n_instrument":8,"n_unverified":2,"n_samples":12,"n_pointer_only_licence":0,"sample_list":"/paper/dart-math-difficulty-aware-rejection-tuning-1#ran","syntology_url":"https://syntology.ai/paper/2407.13690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.13690"}}}},{"rank_in_archive_order":41,"model":"Gemini Ultra (4-shot)","metrics":{"Accuracy":"53.2"},"uses_additional_data":false,"paper_date":"2023-12-19","paper":"/paper/gemini-a-family-of-highly-capable-multimodal-1","paper_url":"https://arxiv.org/abs/2312.11805v5","paper_title":"Gemini: A Family of Highly Capable Multimodal Models","code":"https://github.com/valdecy/pybibx","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":42,"model":"DART-Math-DSMath-7B-Uniform (0-shot CoT, w/o code)","metrics":{"Accuracy":"52.9","Parameters (Billions)":"7"},"uses_additional_data":true,"paper_date":"2024-06-18","paper":"/paper/dart-math-difficulty-aware-rejection-tuning-1","paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","code":"https://github.com/hkust-nlp/dart-math","n_code_links":1,"official":{"repos":["hkust-nlp/dart-math"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":2,"n_instrument":8,"n_unverified":2,"n_samples":12,"n_pointer_only_licence":0,"sample_list":"/paper/dart-math-difficulty-aware-rejection-tuning-1#ran","syntology_url":"https://syntology.ai/paper/2407.13690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.13690"}}}},{"rank_in_archive_order":43,"model":"GPT-4 model (w/ code, PAL)","metrics":{"Accuracy":"51.8"},"uses_additional_data":false,"paper_date":"2022-11-18","paper":"/paper/pal-program-aided-language-models","paper_url":"https://arxiv.org/abs/2211.10435v2","paper_title":"PAL: Program-aided Language Models","code":"https://github.com/srush/minichain","n_code_links":3,"official":null,"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/pal-program-aided-language-models#ran","syntology_url":"https://syntology.ai/paper/2211.10435","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.10435"}}}},{"rank_in_archive_order":44,"model":"DeepSeekMATH-RL-7B (greedy decoding)","metrics":{"Accuracy":"51.7","Parameters (Billions)":"7"},"uses_additional_data":true,"paper_date":"2024-02-05","paper":"/paper/deepseekmath-pushing-the-limits-of","paper_url":"https://arxiv.org/abs/2402.03300v3","paper_title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","code":"https://github.com/shibing624/medicalgpt","n_code_links":5,"official":{"repos":["deepseek-ai/deepseek-math"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":14,"n_constructed":0,"n_ran_checked":3,"n_instrument":11,"n_unverified":10,"n_samples":24,"n_pointer_only_licence":3,"sample_list":"/paper/deepseekmath-pushing-the-limits-of#ran","syntology_url":"https://syntology.ai/paper/2402.03300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03300"}}}},{"rank_in_archive_order":45,"model":"AlphaLLM (with MCTS)","metrics":{"Accuracy":"51"},"uses_additional_data":false,"paper_date":"2024-04-18","paper":"/paper/toward-self-improvement-of-llms-via","paper_url":"https://arxiv.org/abs/2404.12253v2","paper_title":"Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing","code":"https://github.com/yetianjhu/alphallm","n_code_links":1,"official":{"repos":["yetianjhu/alphallm"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":1,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]},"syntology":{"n_ran":14,"n_constructed":1,"n_ran_checked":5,"n_instrument":9,"n_unverified":4,"n_samples":18,"n_pointer_only_licence":18,"sample_list":"/paper/toward-self-improvement-of-llms-via#ran","syntology_url":"https://syntology.ai/paper/2404.12253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.12253"}}}},{"rank_in_archive_order":46,"model":"ToRA-Code 34B (w/ code)","metrics":{"Accuracy":"50.8","Parameters (Billions)":"34"},"uses_additional_data":true,"paper_date":"2023-09-29","paper":"/paper/tora-a-tool-integrated-reasoning-agent-for","paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","code":"https://github.com/microsoft/tora","n_code_links":1,"official":{"repos":["microsoft/tora"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":1,"n_samples":12,"n_pointer_only_licence":9,"sample_list":"/paper/tora-a-tool-integrated-reasoning-agent-for#ran","syntology_url":"https://syntology.ai/paper/2309.17452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17452"}}}},{"rank_in_archive_order":47,"model":"OpenMath-CodeLlama-70B (w/ code)","metrics":{"Accuracy":"50.7","Parameters (Billions)":"70"},"uses_additional_data":true,"paper_date":"2024-02-15","paper":"/paper/openmathinstruct-1-a-1-8-million-math","paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","code":"https://github.com/kipok/nemo-skills","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":48,"model":"Minerva 540B (maj1@k, k=64)","metrics":{"Accuracy":"50.3"},"uses_additional_data":false,"paper_date":"2022-06-29","paper":"/paper/solving-quantitative-reasoning-problems-with","paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","code":"https://github.com/gair-nlp/abel","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":49,"model":"ToRA 70B (w/ code)","metrics":{"Accuracy":"49.7","Parameters (Billions)":"70"},"uses_additional_data":true,"paper_date":"2023-09-29","paper":"/paper/tora-a-tool-integrated-reasoning-agent-for","paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","code":"https://github.com/microsoft/tora","n_code_links":1,"official":{"repos":["microsoft/tora"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":1,"n_samples":12,"n_pointer_only_licence":9,"sample_list":"/paper/tora-a-tool-integrated-reasoning-agent-for#ran","syntology_url":"https://syntology.ai/paper/2309.17452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17452"}}}},{"rank_in_archive_order":50,"model":"MMOS-CODE-34B(0-shot)","metrics":{"Accuracy":"49.5","Parameters (Billions)":"34"},"uses_additional_data":true,"paper_date":"2024-02-23","paper":"/paper/an-empirical-study-of-data-ability-boundary","paper_url":"https://arxiv.org/abs/2403.00799v1","paper_title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","code":"https://github.com/cyzhh/MMOS","n_code_links":1,"official":{"repos":["cyzhh/MMOS"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":2,"n_samples":11,"n_pointer_only_licence":11,"sample_list":"/paper/an-empirical-study-of-data-ability-boundary#ran","syntology_url":"https://syntology.ai/paper/2403.00799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00799"}}}},{"rank_in_archive_order":51,"model":"DeepSeekMath-7B-KPMath-Plus","metrics":{"Accuracy":"48.8","Parameters (Billions)":"7"},"uses_additional_data":false,"paper_date":"2024-03-04","paper":"/paper/key-point-driven-data-synthesis-with-its","paper_url":"https://arxiv.org/abs/2403.02333v3","paper_title":"Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":52,"model":"PaLM 2 (few-shot, k=4, SC)","metrics":{"Accuracy":"48.8"},"uses_additional_data":false,"paper_date":"2023-05-17","paper":"/paper/palm-2-technical-report-1","paper_url":"https://arxiv.org/abs/2305.10403v3","paper_title":"PaLM 2 Technical Report","code":"https://github.com/eternityyw/tram-benchmark","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":53,"model":"Llemma-34B-KPMath-Plus","metrics":{"Accuracy":"48.6","Parameters (Billions)":"34"},"uses_additional_data":false,"paper_date":"2024-03-04","paper":"/paper/key-point-driven-data-synthesis-with-its","paper_url":"https://arxiv.org/abs/2403.02333v3","paper_title":"Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":54,"model":"OpenMath-CodeLlama-34B (w/ code)","metrics":{"Accuracy":"48.3","Parameters (Billions)":"34"},"uses_additional_data":true,"paper_date":"2024-02-15","paper":"/paper/openmathinstruct-1-a-1-8-million-math","paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","code":"https://github.com/kipok/nemo-skills","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":55,"model":"Shepherd + DeepSeek-67B (SFT on MetaMATH + PRM rerank, k=256)","metrics":{"Accuracy":"48.1","Parameters (Billions)":"67"},"uses_additional_data":true,"paper_date":"2023-12-14","paper":"/paper/math-shepherd-a-label-free-step-by-step","paper_url":"https://arxiv.org/abs/2312.08935v3","paper_title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations","code":"https://github.com/hkust-nlp/b-star","n_code_links":3,"official":null,"syntology":null},{"rank_in_archive_order":56,"model":"ToRA-Code 13B (w/ code)","metrics":{"Accuracy":"48.1","Parameters (Billions)":"13"},"uses_additional_data":true,"paper_date":"2023-09-29","paper":"/paper/tora-a-tool-integrated-reasoning-agent-for","paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","code":"https://github.com/microsoft/tora","n_code_links":1,"official":{"repos":["microsoft/tora"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":1,"n_samples":12,"n_pointer_only_licence":9,"sample_list":"/paper/tora-a-tool-integrated-reasoning-agent-for#ran","syntology_url":"https://syntology.ai/paper/2309.17452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17452"}}}},{"rank_in_archive_order":57,"model":"Minerva 8B (maj5@256)","metrics":{"Accuracy":"47.6","Parameters (Billions)":"8"},"uses_additional_data":false,"paper_date":"2022-06-29","paper":"/paper/solving-quantitative-reasoning-problems-with","paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","code":"https://github.com/gair-nlp/abel","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":58,"model":"Mistral-7B-KPMath-Plus","metrics":{"Accuracy":"46.8","Parameters (Billions)":"7"},"uses_additional_data":true,"paper_date":"2024-03-04","paper":"/paper/key-point-driven-data-synthesis-with-its","paper_url":"https://arxiv.org/abs/2403.02333v3","paper_title":"Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":59,"model":"DART-Math-Llama3-8B-Prop2Diff (0-shot CoT, w/o code)","metrics":{"Accuracy":"46.6","Parameters (Billions)":"8"},"uses_additional_data":true,"paper_date":"2024-06-18","paper":"/paper/dart-math-difficulty-aware-rejection-tuning-1","paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","code":"https://github.com/hkust-nlp/dart-math","n_code_links":1,"official":{"repos":["hkust-nlp/dart-math"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":2,"n_instrument":8,"n_unverified":2,"n_samples":12,"n_pointer_only_licence":0,"sample_list":"/paper/dart-math-difficulty-aware-rejection-tuning-1#ran","syntology_url":"https://syntology.ai/paper/2407.13690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.13690"}}}},{"rank_in_archive_order":60,"model":"OpenMath-Llama2-70B (w/ code)","metrics":{"Accuracy":"46.3","Parameters (Billions)":"70"},"uses_additional_data":true,"paper_date":"2024-02-15","paper":"/paper/openmathinstruct-1-a-1-8-million-math","paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","code":"https://github.com/kipok/nemo-skills","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":61,"model":"OpenMath-CodeLlama-13B (w/ code)","metrics":{"Accuracy":"45.5","Parameters (Billions)":"13"},"uses_additional_data":true,"paper_date":"2024-02-15","paper":"/paper/openmathinstruct-1-a-1-8-million-math","paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","code":"https://github.com/kipok/nemo-skills","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":62,"model":"DART-Math-Mistral-7B-Prop2Diff (0-shot CoT, w/o code)","metrics":{"Accuracy":"45.5","Parameters (Billions)":"7"},"uses_additional_data":true,"paper_date":"2024-06-18","paper":"/paper/dart-math-difficulty-aware-rejection-tuning-1","paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","code":"https://github.com/hkust-nlp/dart-math","n_code_links":1,"official":{"repos":["hkust-nlp/dart-math"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":2,"n_instrument":8,"n_unverified":2,"n_samples":12,"n_pointer_only_licence":0,"sample_list":"/paper/dart-math-difficulty-aware-rejection-tuning-1#ran","syntology_url":"https://syntology.ai/paper/2407.13690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.13690"}}}},{"rank_in_archive_order":63,"model":"DART-Math-Llama3-8B-Uniform (0-shot CoT, w/o code)","metrics":{"Accuracy":"45.3","Parameters (Billions)":"8"},"uses_additional_data":true,"paper_date":"2024-06-18","paper":"/paper/dart-math-difficulty-aware-rejection-tuning-1","paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","code":"https://github.com/hkust-nlp/dart-math","n_code_links":1,"official":{"repos":["hkust-nlp/dart-math"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":2,"n_instrument":8,"n_unverified":2,"n_samples":12,"n_pointer_only_licence":0,"sample_list":"/paper/dart-math-difficulty-aware-rejection-tuning-1#ran","syntology_url":"https://syntology.ai/paper/2407.13690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.13690"}}}},{"rank_in_archive_order":64,"model":"MathCoder-CL-34B","metrics":{"Accuracy":"45.2","Parameters (Billions)":"34"},"uses_additional_data":true,"paper_date":"2023-10-05","paper":"/paper/mathcoder-seamless-code-integration-in-llms","paper_url":"https://arxiv.org/abs/2310.03731v1","paper_title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","code":"https://github.com/mathllm/mathcoder","n_code_links":1,"official":{"repos":["mathllm/mathcoder"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/mathcoder-seamless-code-integration-in-llms#ran","syntology_url":"https://syntology.ai/paper/2310.03731","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03731"}}}},{"rank_in_archive_order":65,"model":"MathCoder-L-34B","metrics":{"Accuracy":"45.1","Parameters (Billions)":"34"},"uses_additional_data":true,"paper_date":"2023-10-05","paper":"/paper/mathcoder-seamless-code-integration-in-llms","paper_url":"https://arxiv.org/abs/2310.03731v1","paper_title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","code":"https://github.com/mathllm/mathcoder","n_code_links":1,"official":{"repos":["mathllm/mathcoder"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/mathcoder-seamless-code-integration-in-llms#ran","syntology_url":"https://syntology.ai/paper/2310.03731","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03731"}}}},{"rank_in_archive_order":66,"model":"MMIQC-72B","metrics":{"Accuracy":"45.0","Parameters (Billions)":"72"},"uses_additional_data":true,"paper_date":"2024-01-17","paper":"/paper/augmenting-math-word-problems-via-iterative","paper_url":"https://arxiv.org/abs/2401.09003v5","paper_title":"Augmenting Math Word Problems via Iterative Question Composing","code":"https://github.com/iiis-ai/iterativequestioncomposing","n_code_links":1,"official":{"repos":["iiis-ai/iterativequestioncomposing"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":4,"sample_list":"/paper/augmenting-math-word-problems-via-iterative#ran","syntology_url":"https://syntology.ai/paper/2401.09003","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.09003"}}}},{"rank_in_archive_order":67,"model":"ToRA-Code 7B (w/ code)","metrics":{"Accuracy":"44.6","Parameters (Billions)":"7"},"uses_additional_data":true,"paper_date":"2023-09-29","paper":"/paper/tora-a-tool-integrated-reasoning-agent-for","paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","code":"https://github.com/microsoft/tora","n_code_links":1,"official":{"repos":["microsoft/tora"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":1,"n_samples":12,"n_pointer_only_licence":9,"sample_list":"/paper/tora-a-tool-integrated-reasoning-agent-for#ran","syntology_url":"https://syntology.ai/paper/2309.17452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17452"}}}},{"rank_in_archive_order":68,"model":"OpenMath-Mistral-7B (w/ code)","metrics":{"Accuracy":"44.5","Parameters (Billions)":"7"},"uses_additional_data":true,"paper_date":"2024-02-15","paper":"/paper/openmathinstruct-1-a-1-8-million-math","paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","code":"https://github.com/kipok/nemo-skills","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":69,"model":"MMOS-CODE-7B(0-shot)","metrics":{"Accuracy":"44.3","Parameters (Billions)":"7"},"uses_additional_data":true,"paper_date":"2024-02-23","paper":"/paper/an-empirical-study-of-data-ability-boundary","paper_url":"https://arxiv.org/abs/2403.00799v1","paper_title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","code":"https://github.com/cyzhh/MMOS","n_code_links":1,"official":{"repos":["cyzhh/MMOS"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":2,"n_samples":11,"n_pointer_only_licence":11,"sample_list":"/paper/an-empirical-study-of-data-ability-boundary#ran","syntology_url":"https://syntology.ai/paper/2403.00799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00799"}}}},{"rank_in_archive_order":70,"model":"OpenMath-CodeLlama-7B (w/ code)","metrics":{"Accuracy":"43.6","Parameters (Billions)":"7"},"uses_additional_data":true,"paper_date":"2024-02-15","paper":"/paper/openmathinstruct-1-a-1-8-million-math","paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","code":"https://github.com/kipok/nemo-skills","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":71,"model":"Shepherd+Mistral-7B (SFT on MetaMATH + PRM RL+ PRM rerank, k=256)","metrics":{"Accuracy":"43.5","Parameters (Billions)":"7"},"uses_additional_data":true,"paper_date":"2023-12-14","paper":"/paper/math-shepherd-a-label-free-step-by-step","paper_url":"https://arxiv.org/abs/2312.08935v3","paper_title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations","code":"https://github.com/hkust-nlp/b-star","n_code_links":3,"official":null,"syntology":null},{"rank_in_archive_order":72,"model":"DART-Math-Mistral-7B-Uniform (0-shot CoT, w/o code)","metrics":{"Accuracy":"43.5","Parameters (Billions)":"7"},"uses_additional_data":true,"paper_date":"2024-06-18","paper":"/paper/dart-math-difficulty-aware-rejection-tuning-1","paper_url":"https://arxiv.org/abs/2407.13690v2","paper_title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","code":"https://github.com/hkust-nlp/dart-math","n_code_links":1,"official":{"repos":["hkust-nlp/dart-math"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":2,"n_instrument":8,"n_unverified":2,"n_samples":12,"n_pointer_only_licence":0,"sample_list":"/paper/dart-math-difficulty-aware-rejection-tuning-1#ran","syntology_url":"https://syntology.ai/paper/2407.13690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.13690"}}}},{"rank_in_archive_order":73,"model":"Minerva 62B (maj1@k, k=64)","metrics":{"Accuracy":"43.4","Parameters (Billions)":"62"},"uses_additional_data":false,"paper_date":"2022-06-29","paper":"/paper/solving-quantitative-reasoning-problems-with","paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","code":"https://github.com/gair-nlp/abel","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":74,"model":"ToRA 13B (w/ code)","metrics":{"Accuracy":"43.0","Parameters (Billions)":"13"},"uses_additional_data":true,"paper_date":"2023-09-29","paper":"/paper/tora-a-tool-integrated-reasoning-agent-for","paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","code":"https://github.com/microsoft/tora","n_code_links":1,"official":{"repos":["microsoft/tora"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":1,"n_samples":12,"n_pointer_only_licence":9,"sample_list":"/paper/tora-a-tool-integrated-reasoning-agent-for#ran","syntology_url":"https://syntology.ai/paper/2309.17452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17452"}}}},{"rank_in_archive_order":75,"model":"GPT-4","metrics":{"Accuracy":"42.5"},"uses_additional_data":false,"paper_date":"2023-03-22","paper":"/paper/sparks-of-artificial-general-intelligence","paper_url":"https://arxiv.org/abs/2303.12712v5","paper_title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","code":"https://github.com/microsoft/guidance","n_code_links":3,"official":null,"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_samples":10,"n_pointer_only_licence":0,"sample_list":"/paper/sparks-of-artificial-general-intelligence#ran","syntology_url":"https://syntology.ai/paper/2303.12712","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.12712"}}}},{"rank_in_archive_order":76,"model":"SFT-Mistral-7B","metrics":{"Accuracy":"41.8","Parameters (Billions)":"7"},"uses_additional_data":true,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":77,"model":"Llama2-13B-KPMath-Plus","metrics":{"Accuracy":"41","Parameters (Billions)":"13"},"uses_additional_data":false,"paper_date":"2024-03-04","paper":"/paper/key-point-driven-data-synthesis-with-its","paper_url":"https://arxiv.org/abs/2403.02333v3","paper_title":"Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":78,"model":"ToRA 7B (w/ code)","metrics":{"Accuracy":"40.1","Parameters (Billions)":"7"},"uses_additional_data":true,"paper_date":"2023-09-29","paper":"/paper/tora-a-tool-integrated-reasoning-agent-for","paper_url":"https://arxiv.org/abs/2309.17452v4","paper_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","code":"https://github.com/microsoft/tora","n_code_links":1,"official":{"repos":["microsoft/tora"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":1,"n_samples":12,"n_pointer_only_licence":9,"sample_list":"/paper/tora-a-tool-integrated-reasoning-agent-for#ran","syntology_url":"https://syntology.ai/paper/2309.17452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17452"}}}},{"rank_in_archive_order":79,"model":"MathCoder-CL-13B","metrics":{"Accuracy":"35.9","Parameters (Billions)":"13"},"uses_additional_data":true,"paper_date":"2023-10-05","paper":"/paper/mathcoder-seamless-code-integration-in-llms","paper_url":"https://arxiv.org/abs/2310.03731v1","paper_title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","code":"https://github.com/mathllm/mathcoder","n_code_links":1,"official":{"repos":["mathllm/mathcoder"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/mathcoder-seamless-code-integration-in-llms#ran","syntology_url":"https://syntology.ai/paper/2310.03731","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03731"}}}},{"rank_in_archive_order":80,"model":"MuggleMATH-70B","metrics":{"Accuracy":"35.6","Parameters (Billions)":"70"},"uses_additional_data":true,"paper_date":"2023-10-09","paper":"/paper/query-and-response-augmentation-cannot-help","paper_url":"https://arxiv.org/abs/2310.05506v3","paper_title":"MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoning","code":"https://github.com/ofa-sys/gsm8k-screl","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":81,"model":"PaLM 2 (few-shot, k=4, CoT)","metrics":{"Accuracy":"34.3"},"uses_additional_data":false,"paper_date":"2023-05-17","paper":"/paper/palm-2-technical-report-1","paper_url":"https://arxiv.org/abs/2305.10403v3","paper_title":"PaLM 2 Technical Report","code":"https://github.com/eternityyw/tram-benchmark","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":82,"model":"Minerva 540B","metrics":{"Accuracy":"33.6","Parameters (Billions)":"540"},"uses_additional_data":false,"paper_date":"2022-06-29","paper":"/paper/solving-quantitative-reasoning-problems-with","paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","code":"https://github.com/gair-nlp/abel","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":83,"model":"Minerva 540B (5-shot) mCoT","metrics":{"Accuracy":"33.6","Parameters (Billions)":"540"},"uses_additional_data":false,"paper_date":"2022-11-16","paper":"/paper/galactica-a-large-language-model-for-science-1","paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","code":"https://github.com/paperswithcode/galai","n_code_links":1,"official":{"repos":["paperswithcode/galai"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/galactica-a-large-language-model-for-science-1#ran","syntology_url":"https://syntology.ai/paper/2211.09085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09085"}}}},{"rank_in_archive_order":84,"model":"Shepherd + Mistral-7B (SFT on MetaMATH + PRM RL)","metrics":{"Accuracy":"33.0","Parameters (Billions)":"7"},"uses_additional_data":true,"paper_date":"2023-12-14","paper":"/paper/math-shepherd-a-label-free-step-by-step","paper_url":"https://arxiv.org/abs/2312.08935v3","paper_title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations","code":"https://github.com/hkust-nlp/b-star","n_code_links":3,"official":null,"syntology":null},{"rank_in_archive_order":85,"model":"WizardMath-7B-V1.1","metrics":{"Accuracy":"33.0","Parameters (Billions)":"7"},"uses_additional_data":true,"paper_date":"2023-08-18","paper":"/paper/wizardmath-empowering-mathematical-reasoning","paper_url":"https://arxiv.org/abs/2308.09583v2","paper_title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","code":"https://github.com/nlpxucan/wizardlm","n_code_links":1,"official":null,"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":6,"n_samples":16,"n_pointer_only_licence":16,"sample_list":"/paper/wizardmath-empowering-mathematical-reasoning#ran","syntology_url":"https://syntology.ai/paper/2308.09583","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09583"}}}},{"rank_in_archive_order":86,"model":"Gemini Pro (4-shot)","metrics":{"Accuracy":"32.6"},"uses_additional_data":false,"paper_date":"2023-12-19","paper":"/paper/gemini-a-family-of-highly-capable-multimodal-1","paper_url":"https://arxiv.org/abs/2312.11805v5","paper_title":"Gemini: A Family of Highly Capable Multimodal Models","code":"https://github.com/valdecy/pybibx","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":87,"model":"MuggleMATH-13B","metrics":{"Accuracy":"30.7","Parameters (Billions)":"13"},"uses_additional_data":true,"paper_date":"2023-10-09","paper":"/paper/query-and-response-augmentation-cannot-help","paper_url":"https://arxiv.org/abs/2310.05506v3","paper_title":"MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoning","code":"https://github.com/ofa-sys/gsm8k-screl","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":88,"model":"MathCoder-CL-7B","metrics":{"Accuracy":"30.2","Parameters (Billions)":"7"},"uses_additional_data":true,"paper_date":"2023-10-05","paper":"/paper/mathcoder-seamless-code-integration-in-llms","paper_url":"https://arxiv.org/abs/2310.03731v1","paper_title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","code":"https://github.com/mathllm/mathcoder","n_code_links":1,"official":{"repos":["mathllm/mathcoder"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/mathcoder-seamless-code-integration-in-llms#ran","syntology_url":"https://syntology.ai/paper/2310.03731","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03731"}}}},{"rank_in_archive_order":89,"model":"MathCoder-L-13B","metrics":{"Accuracy":"29.9","Parameters (Billions)":"13"},"uses_additional_data":true,"paper_date":"2023-10-05","paper":"/paper/mathcoder-seamless-code-integration-in-llms","paper_url":"https://arxiv.org/abs/2310.03731v1","paper_title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","code":"https://github.com/mathllm/mathcoder","n_code_links":1,"official":{"repos":["mathllm/mathcoder"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/mathcoder-seamless-code-integration-in-llms#ran","syntology_url":"https://syntology.ai/paper/2310.03731","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03731"}}}},{"rank_in_archive_order":90,"model":"Qwen2idae-16x14B (4-shot)","metrics":{"Accuracy":"29.9"},"uses_additional_data":false,"paper_date":"2024-01-05","paper":"/paper/parameter-efficient-sparsity-crafting-from","paper_url":"https://arxiv.org/abs/2401.02731v4","paper_title":"Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks","code":"https://github.com/wuhy68/parameter-efficient-moe","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":91,"model":"OpenChat-3.5-1210 7B","metrics":{"Accuracy":"28.9","Parameters (Billions)":"7"},"uses_additional_data":false,"paper_date":"2023-09-20","paper":"/paper/openchat-advancing-open-source-language","paper_url":"https://arxiv.org/abs/2309.11235v2","paper_title":"OpenChat: Advancing Open-source Language Models with Mixed-Quality Data","code":"https://github.com/imoneoi/openchat","n_code_links":1,"official":{"repos":["imoneoi/openchat"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/openchat-advancing-open-source-language#ran","syntology_url":"https://syntology.ai/paper/2309.11235","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.11235"}}}},{"rank_in_archive_order":92,"model":"OpenChat-3.5 7B","metrics":{"Accuracy":"28.6","Parameters (Billions)":"7"},"uses_additional_data":false,"paper_date":"2023-09-20","paper":"/paper/openchat-advancing-open-source-language","paper_url":"https://arxiv.org/abs/2309.11235v2","paper_title":"OpenChat: Advancing Open-source Language Models with Mixed-Quality Data","code":"https://github.com/imoneoi/openchat","n_code_links":1,"official":{"repos":["imoneoi/openchat"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/openchat-advancing-open-source-language#ran","syntology_url":"https://syntology.ai/paper/2309.11235","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.11235"}}}},{"rank_in_archive_order":93,"model":"Mixtral 8x7B (maj@4)","metrics":{"Accuracy":"28.4"},"uses_additional_data":false,"paper_date":"2024-01-08","paper":"/paper/mixtral-of-experts","paper_url":"https://arxiv.org/abs/2401.04088v1","paper_title":"Mixtral of Experts","code":"https://github.com/jingyaogong/minimind","n_code_links":6,"official":null,"syntology":{"n_ran":5,"n_constructed":5,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":0,"sample_list":"/paper/mixtral-of-experts#ran","syntology_url":"https://syntology.ai/paper/2401.04088","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.04088"}}}},{"rank_in_archive_order":94,"model":"Minerva 62B (4-shot)","metrics":{"Accuracy":"27.6","Parameters (Billions)":"62"},"uses_additional_data":false,"paper_date":"2022-06-29","paper":"/paper/solving-quantitative-reasoning-problems-with","paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","code":"https://github.com/gair-nlp/abel","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":95,"model":"MetaMath 70B","metrics":{"Accuracy":"26.0","Parameters (Billions)":"70"},"uses_additional_data":true,"paper_date":"2023-09-21","paper":"/paper/metamath-bootstrap-your-own-mathematical","paper_url":"https://arxiv.org/abs/2309.12284v4","paper_title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","code":"https://github.com/meta-math/MetaMath","n_code_links":1,"official":{"repos":["meta-math/MetaMath"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":7,"ran_from_kinds":["official"]},"syntology":{"n_ran":15,"n_constructed":0,"n_ran_checked":1,"n_instrument":14,"n_unverified":7,"n_samples":22,"n_pointer_only_licence":0,"sample_list":"/paper/metamath-bootstrap-your-own-mathematical#ran","syntology_url":"https://syntology.ai/paper/2309.12284","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.12284"}}}},{"rank_in_archive_order":96,"model":"MuggleMATH 7B","metrics":{"Accuracy":"25.8","Parameters (Billions)":"7"},"uses_additional_data":true,"paper_date":"2023-10-09","paper":"/paper/query-and-response-augmentation-cannot-help","paper_url":"https://arxiv.org/abs/2310.05506v3","paper_title":"MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoning","code":"https://github.com/ofa-sys/gsm8k-screl","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":97,"model":"Minerva 8B (maj1@k, k=64)","metrics":{"Accuracy":"25.4","Parameters (Billions)":"8"},"uses_additional_data":false,"paper_date":"2022-06-29","paper":"/paper/solving-quantitative-reasoning-problems-with","paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","code":"https://github.com/gair-nlp/abel","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":98,"model":"MathCoder-L-7B","metrics":{"Accuracy":"23.3","Parameters (Billions)":"7"},"uses_additional_data":true,"paper_date":"2023-10-05","paper":"/paper/mathcoder-seamless-code-integration-in-llms","paper_url":"https://arxiv.org/abs/2310.03731v1","paper_title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","code":"https://github.com/mathllm/mathcoder","n_code_links":1,"official":{"repos":["mathllm/mathcoder"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/mathcoder-seamless-code-integration-in-llms#ran","syntology_url":"https://syntology.ai/paper/2310.03731","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03731"}}}},{"rank_in_archive_order":99,"model":"WizardMath-70B-V1.0","metrics":{"Accuracy":"22.7","Parameters (Billions)":"70"},"uses_additional_data":true,"paper_date":"2023-08-18","paper":"/paper/wizardmath-empowering-mathematical-reasoning","paper_url":"https://arxiv.org/abs/2308.09583v2","paper_title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","code":"https://github.com/nlpxucan/wizardlm","n_code_links":1,"official":null,"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":6,"n_samples":16,"n_pointer_only_licence":16,"sample_list":"/paper/wizardmath-empowering-mathematical-reasoning#ran","syntology_url":"https://syntology.ai/paper/2308.09583","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09583"}}}},{"rank_in_archive_order":100,"model":"Camelidae-8×34B (4-shot)","metrics":{"Accuracy":"22.6"},"uses_additional_data":false,"paper_date":"2024-01-05","paper":"/paper/parameter-efficient-sparsity-crafting-from","paper_url":"https://arxiv.org/abs/2401.02731v4","paper_title":"Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks","code":"https://github.com/wuhy68/parameter-efficient-moe","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":101,"model":"MetaMath 13B","metrics":{"Accuracy":"22.5","Parameters (Billions)":"13"},"uses_additional_data":true,"paper_date":"2023-09-21","paper":"/paper/metamath-bootstrap-your-own-mathematical","paper_url":"https://arxiv.org/abs/2309.12284v4","paper_title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","code":"https://github.com/meta-math/MetaMath","n_code_links":1,"official":{"repos":["meta-math/MetaMath"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":7,"ran_from_kinds":["official"]},"syntology":{"n_ran":15,"n_constructed":0,"n_ran_checked":1,"n_instrument":14,"n_unverified":7,"n_samples":22,"n_pointer_only_licence":0,"sample_list":"/paper/metamath-bootstrap-your-own-mathematical#ran","syntology_url":"https://syntology.ai/paper/2309.12284","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.12284"}}}},{"rank_in_archive_order":102,"model":"LLaMA 65B (maj1@k)","metrics":{"Accuracy":"20.5","Parameters (Billions)":"65"},"uses_additional_data":false,"paper_date":"2023-02-27","paper":"/paper/llama-open-and-efficient-foundation-language-1","paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","code":"https://github.com/huggingface/transformers","n_code_links":57,"official":{"repos":["facebookresearch/llama"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"syntology":{"n_ran":37,"n_constructed":9,"n_ran_checked":25,"n_instrument":12,"n_unverified":21,"n_samples":58,"n_pointer_only_licence":4,"sample_list":"/paper/llama-open-and-efficient-foundation-language-1#ran","syntology_url":"https://syntology.ai/paper/2302.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13971"}}}},{"rank_in_archive_order":103,"model":"GAL 120B (5-shot) mCoT","metrics":{"Accuracy":"20.4","Parameters (Billions)":"120"},"uses_additional_data":false,"paper_date":"2022-11-16","paper":"/paper/galactica-a-large-language-model-for-science-1","paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","code":"https://github.com/paperswithcode/galai","n_code_links":1,"official":{"repos":["paperswithcode/galai"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/galactica-a-large-language-model-for-science-1#ran","syntology_url":"https://syntology.ai/paper/2211.09085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09085"}}}},{"rank_in_archive_order":104,"model":"MetaMath 7B","metrics":{"Accuracy":"19.4","Parameters (Billions)":"7"},"uses_additional_data":true,"paper_date":"2023-09-21","paper":"/paper/metamath-bootstrap-your-own-mathematical","paper_url":"https://arxiv.org/abs/2309.12284v4","paper_title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","code":"https://github.com/meta-math/MetaMath","n_code_links":1,"official":{"repos":["meta-math/MetaMath"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":7,"ran_from_kinds":["official"]},"syntology":{"n_ran":15,"n_constructed":0,"n_ran_checked":1,"n_instrument":14,"n_unverified":7,"n_samples":22,"n_pointer_only_licence":0,"sample_list":"/paper/metamath-bootstrap-your-own-mathematical#ran","syntology_url":"https://syntology.ai/paper/2309.12284","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.12284"}}}},{"rank_in_archive_order":105,"model":"davinci-002 175B","metrics":{"Accuracy":"19.1","Parameters (Billions)":"175"},"uses_additional_data":false,"paper_date":"2022-06-29","paper":"/paper/solving-quantitative-reasoning-problems-with","paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","code":"https://github.com/gair-nlp/abel","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":106,"model":"Branch-Train-MiX 4x7B (sampling top-2 experts)","metrics":{"Accuracy":"17.8"},"uses_additional_data":false,"paper_date":"2024-03-12","paper":"/paper/branch-train-mix-mixing-expert-llms-into-a","paper_url":"https://arxiv.org/abs/2403.07816v1","paper_title":"Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM","code":"https://github.com/Leeroo-AI/mergoo","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":107,"model":"GAL 120B <work>","metrics":{"Accuracy":"16.6","Parameters (Billions)":"120"},"uses_additional_data":false,"paper_date":"2022-11-16","paper":"/paper/galactica-a-large-language-model-for-science-1","paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","code":"https://github.com/paperswithcode/galai","n_code_links":1,"official":{"repos":["paperswithcode/galai"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/galactica-a-large-language-model-for-science-1#ran","syntology_url":"https://syntology.ai/paper/2211.09085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09085"}}}},{"rank_in_archive_order":108,"model":"LLaMA 33B-maj1@k","metrics":{"Accuracy":"15.2","Parameters (Billions)":"33"},"uses_additional_data":false,"paper_date":"2023-02-27","paper":"/paper/llama-open-and-efficient-foundation-language-1","paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","code":"https://github.com/huggingface/transformers","n_code_links":57,"official":{"repos":["facebookresearch/llama"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"syntology":{"n_ran":37,"n_constructed":9,"n_ran_checked":25,"n_instrument":12,"n_unverified":21,"n_samples":58,"n_pointer_only_licence":4,"sample_list":"/paper/llama-open-and-efficient-foundation-language-1#ran","syntology_url":"https://syntology.ai/paper/2302.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13971"}}}},{"rank_in_archive_order":109,"model":"Minerva 8B","metrics":{"Accuracy":"14.1","Parameters (Billions)":"8"},"uses_additional_data":false,"paper_date":"2022-06-29","paper":"/paper/solving-quantitative-reasoning-problems-with","paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","code":"https://github.com/gair-nlp/abel","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":110,"model":"WizardMath-13B-V1.0","metrics":{"Accuracy":"14.0","Parameters (Billions)":"13"},"uses_additional_data":true,"paper_date":"2023-08-18","paper":"/paper/wizardmath-empowering-mathematical-reasoning","paper_url":"https://arxiv.org/abs/2308.09583v2","paper_title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","code":"https://github.com/nlpxucan/wizardlm","n_code_links":1,"official":null,"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":6,"n_samples":16,"n_pointer_only_licence":16,"sample_list":"/paper/wizardmath-empowering-mathematical-reasoning#ran","syntology_url":"https://syntology.ai/paper/2308.09583","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09583"}}}},{"rank_in_archive_order":111,"model":"Mistral 7B (maj@4)","metrics":{"Accuracy":"13.1","Parameters (Billions)":"7"},"uses_additional_data":false,"paper_date":"2023-10-10","paper":"/paper/mistral-7b","paper_url":"https://arxiv.org/abs/2310.06825v1","paper_title":"Mistral 7B","code":"https://github.com/mistralai/mistral-src","n_code_links":6,"official":{"repos":["mistralai/mistral-src"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_samples":11,"n_pointer_only_licence":2,"sample_list":"/paper/mistral-7b#ran","syntology_url":"https://syntology.ai/paper/2310.06825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06825"}}}},{"rank_in_archive_order":112,"model":"GAL 30B (5-shot) mCoT","metrics":{"Accuracy":"12.7","Parameters (Billions)":"30"},"uses_additional_data":false,"paper_date":"2022-11-16","paper":"/paper/galactica-a-large-language-model-for-science-1","paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","code":"https://github.com/paperswithcode/galai","n_code_links":1,"official":{"repos":["paperswithcode/galai"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/galactica-a-large-language-model-for-science-1#ran","syntology_url":"https://syntology.ai/paper/2211.09085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09085"}}}},{"rank_in_archive_order":113,"model":"Mistral 7B (maj@4)","metrics":{"Accuracy":"12.7","Parameters (Billions)":"7"},"uses_additional_data":false,"paper_date":"2024-01-08","paper":"/paper/mixtral-of-experts","paper_url":"https://arxiv.org/abs/2401.04088v1","paper_title":"Mixtral of Experts","code":"https://github.com/jingyaogong/minimind","n_code_links":6,"official":null,"syntology":{"n_ran":5,"n_constructed":5,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":0,"sample_list":"/paper/mixtral-of-experts#ran","syntology_url":"https://syntology.ai/paper/2401.04088","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.04088"}}}},{"rank_in_archive_order":114,"model":"GAL 30B <work>","metrics":{"Accuracy":"11.4","Parameters (Billions)":"30"},"uses_additional_data":false,"paper_date":"2022-11-16","paper":"/paper/galactica-a-large-language-model-for-science-1","paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","code":"https://github.com/paperswithcode/galai","n_code_links":1,"official":{"repos":["paperswithcode/galai"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/galactica-a-large-language-model-for-science-1#ran","syntology_url":"https://syntology.ai/paper/2211.09085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09085"}}}},{"rank_in_archive_order":115,"model":"WizardMath-7B-V1.0","metrics":{"Accuracy":"10.7","Parameters (Billions)":"7"},"uses_additional_data":true,"paper_date":"2023-08-18","paper":"/paper/wizardmath-empowering-mathematical-reasoning","paper_url":"https://arxiv.org/abs/2308.09583v2","paper_title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","code":"https://github.com/nlpxucan/wizardlm","n_code_links":1,"official":null,"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":6,"n_samples":16,"n_pointer_only_licence":16,"sample_list":"/paper/wizardmath-empowering-mathematical-reasoning#ran","syntology_url":"https://syntology.ai/paper/2308.09583","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09583"}}}},{"rank_in_archive_order":116,"model":"LLaMA 65B","metrics":{"Accuracy":"10.6","Parameters (Billions)":"65"},"uses_additional_data":false,"paper_date":"2023-02-27","paper":"/paper/llama-open-and-efficient-foundation-language-1","paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","code":"https://github.com/huggingface/transformers","n_code_links":57,"official":{"repos":["facebookresearch/llama"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"syntology":{"n_ran":37,"n_constructed":9,"n_ran_checked":25,"n_instrument":12,"n_unverified":21,"n_samples":58,"n_pointer_only_licence":4,"sample_list":"/paper/llama-open-and-efficient-foundation-language-1#ran","syntology_url":"https://syntology.ai/paper/2302.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13971"}}}},{"rank_in_archive_order":117,"model":"PaLM 540B","metrics":{"Accuracy":"8.8","Parameters (Billions)":"540"},"uses_additional_data":false,"paper_date":"2022-06-29","paper":"/paper/solving-quantitative-reasoning-problems-with","paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","code":"https://github.com/gair-nlp/abel","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":118,"model":"PaLM 540B (5-shot) mCoT","metrics":{"Accuracy":"8.8","Parameters (Billions)":"540"},"uses_additional_data":false,"paper_date":"2022-11-16","paper":"/paper/galactica-a-large-language-model-for-science-1","paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","code":"https://github.com/paperswithcode/galai","n_code_links":1,"official":{"repos":["paperswithcode/galai"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/galactica-a-large-language-model-for-science-1#ran","syntology_url":"https://syntology.ai/paper/2211.09085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09085"}}}},{"rank_in_archive_order":119,"model":"LLaMA 13B-maj1@k","metrics":{"Accuracy":"8.8","Parameters (Billions)":"13"},"uses_additional_data":false,"paper_date":"2023-02-27","paper":"/paper/llama-open-and-efficient-foundation-language-1","paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","code":"https://github.com/huggingface/transformers","n_code_links":57,"official":{"repos":["facebookresearch/llama"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"syntology":{"n_ran":37,"n_constructed":9,"n_ran_checked":25,"n_instrument":12,"n_unverified":21,"n_samples":58,"n_pointer_only_licence":4,"sample_list":"/paper/llama-open-and-efficient-foundation-language-1#ran","syntology_url":"https://syntology.ai/paper/2302.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13971"}}}},{"rank_in_archive_order":120,"model":"LLaMA 33B","metrics":{"Accuracy":"7.1","Parameters (Billions)":"33"},"uses_additional_data":false,"paper_date":"2023-02-27","paper":"/paper/llama-open-and-efficient-foundation-language-1","paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","code":"https://github.com/huggingface/transformers","n_code_links":57,"official":{"repos":["facebookresearch/llama"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"syntology":{"n_ran":37,"n_constructed":9,"n_ran_checked":25,"n_instrument":12,"n_unverified":21,"n_samples":58,"n_pointer_only_licence":4,"sample_list":"/paper/llama-open-and-efficient-foundation-language-1#ran","syntology_url":"https://syntology.ai/paper/2302.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13971"}}}},{"rank_in_archive_order":121,"model":"LLaMA 7B-maj1@k","metrics":{"Accuracy":"6.9","Parameters (Billions)":"7"},"uses_additional_data":false,"paper_date":"2023-02-27","paper":"/paper/llama-open-and-efficient-foundation-language-1","paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","code":"https://github.com/huggingface/transformers","n_code_links":57,"official":{"repos":["facebookresearch/llama"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"syntology":{"n_ran":37,"n_constructed":9,"n_ran_checked":25,"n_instrument":12,"n_unverified":21,"n_samples":58,"n_pointer_only_licence":4,"sample_list":"/paper/llama-open-and-efficient-foundation-language-1#ran","syntology_url":"https://syntology.ai/paper/2302.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13971"}}}},{"rank_in_archive_order":122,"model":"GPT-2 (1.5B)","metrics":{"Accuracy":"6.9","Parameters (Billions)":"1.5"},"uses_additional_data":false,"paper_date":"2021-03-05","paper":"/paper/measuring-mathematical-problem-solving-with","paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","code":"https://github.com/hendrycks/math","n_code_links":5,"official":{"repos":["hendrycks/math"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":1,"sample_list":"/paper/measuring-mathematical-problem-solving-with#ran","syntology_url":"https://syntology.ai/paper/2103.03874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.03874"}}}},{"rank_in_archive_order":123,"model":"GPT-2 (0.7B)","metrics":{"Accuracy":"6.4","Parameters (Billions)":"0.7"},"uses_additional_data":false,"paper_date":"2021-03-05","paper":"/paper/measuring-mathematical-problem-solving-with","paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","code":"https://github.com/hendrycks/math","n_code_links":5,"official":{"repos":["hendrycks/math"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":1,"sample_list":"/paper/measuring-mathematical-problem-solving-with#ran","syntology_url":"https://syntology.ai/paper/2103.03874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.03874"}}}},{"rank_in_archive_order":124,"model":"GPT-2 (0.3B)","metrics":{"Accuracy":"6.2","Parameters (Billions)":"0.3"},"uses_additional_data":false,"paper_date":"2021-03-05","paper":"/paper/measuring-mathematical-problem-solving-with","paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","code":"https://github.com/hendrycks/math","n_code_links":5,"official":{"repos":["hendrycks/math"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":1,"sample_list":"/paper/measuring-mathematical-problem-solving-with#ran","syntology_url":"https://syntology.ai/paper/2103.03874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.03874"}}}},{"rank_in_archive_order":125,"model":"GPT-3 13B","metrics":{"Accuracy":"5.6","Parameters (Billions)":"13"},"uses_additional_data":false,"paper_date":"2021-03-05","paper":"/paper/measuring-mathematical-problem-solving-with","paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","code":"https://github.com/hendrycks/math","n_code_links":5,"official":{"repos":["hendrycks/math"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":1,"sample_list":"/paper/measuring-mathematical-problem-solving-with#ran","syntology_url":"https://syntology.ai/paper/2103.03874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.03874"}}}},{"rank_in_archive_order":126,"model":"PaLM 8B (fine-tuned)","metrics":{"Accuracy":"5.6","Parameters (Billions)":"8"},"uses_additional_data":false,"paper_date":"2022-06-29","paper":"/paper/solving-quantitative-reasoning-problems-with","paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","code":"https://github.com/gair-nlp/abel","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":127,"model":"GPT-2 (0.1B)","metrics":{"Accuracy":"5.4","Parameters (Billions)":"0.1"},"uses_additional_data":false,"paper_date":"2021-03-05","paper":"/paper/measuring-mathematical-problem-solving-with","paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","code":"https://github.com/hendrycks/math","n_code_links":5,"official":{"repos":["hendrycks/math"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":1,"sample_list":"/paper/measuring-mathematical-problem-solving-with#ran","syntology_url":"https://syntology.ai/paper/2103.03874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.03874"}}}},{"rank_in_archive_order":128,"model":"GPT-3-175B (few-shot)","metrics":{"Accuracy":"5.2","Parameters (Billions)":"175"},"uses_additional_data":false,"paper_date":"2021-03-05","paper":"/paper/measuring-mathematical-problem-solving-with","paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","code":"https://github.com/hendrycks/math","n_code_links":5,"official":{"repos":["hendrycks/math"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":1,"sample_list":"/paper/measuring-mathematical-problem-solving-with#ran","syntology_url":"https://syntology.ai/paper/2103.03874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.03874"}}}},{"rank_in_archive_order":129,"model":"GPT-3 175B (8-shot)","metrics":{"Accuracy":"5.2","Parameters (Billions)":"175"},"uses_additional_data":false,"paper_date":"2022-11-16","paper":"/paper/galactica-a-large-language-model-for-science-1","paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","code":"https://github.com/paperswithcode/galai","n_code_links":1,"official":{"repos":["paperswithcode/galai"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/galactica-a-large-language-model-for-science-1#ran","syntology_url":"https://syntology.ai/paper/2211.09085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09085"}}}},{"rank_in_archive_order":130,"model":"PaLM 62B","metrics":{"Accuracy":"4.4","Parameters (Billions)":"62"},"uses_additional_data":false,"paper_date":"2022-06-29","paper":"/paper/solving-quantitative-reasoning-problems-with","paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","code":"https://github.com/gair-nlp/abel","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":131,"model":"LLaMA 13B","metrics":{"Accuracy":"3.9","Parameters (Billions)":"13"},"uses_additional_data":false,"paper_date":"2023-02-27","paper":"/paper/llama-open-and-efficient-foundation-language-1","paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","code":"https://github.com/huggingface/transformers","n_code_links":57,"official":{"repos":["facebookresearch/llama"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"syntology":{"n_ran":37,"n_constructed":9,"n_ran_checked":25,"n_instrument":12,"n_unverified":21,"n_samples":58,"n_pointer_only_licence":4,"sample_list":"/paper/llama-open-and-efficient-foundation-language-1#ran","syntology_url":"https://syntology.ai/paper/2302.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13971"}}}},{"rank_in_archive_order":132,"model":"GPT-3-13B (few-shot)","metrics":{"Accuracy":"3.0","Parameters (Billions)":"13"},"uses_additional_data":false,"paper_date":"2021-03-05","paper":"/paper/measuring-mathematical-problem-solving-with","paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","code":"https://github.com/hendrycks/math","n_code_links":5,"official":{"repos":["hendrycks/math"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":1,"sample_list":"/paper/measuring-mathematical-problem-solving-with#ran","syntology_url":"https://syntology.ai/paper/2103.03874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.03874"}}}},{"rank_in_archive_order":133,"model":"LLaMA 7B","metrics":{"Accuracy":"2.9","Parameters (Billions)":"7"},"uses_additional_data":false,"paper_date":"2023-02-27","paper":"/paper/llama-open-and-efficient-foundation-language-1","paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","code":"https://github.com/huggingface/transformers","n_code_links":57,"official":{"repos":["facebookresearch/llama"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"syntology":{"n_ran":37,"n_constructed":9,"n_ran_checked":25,"n_instrument":12,"n_unverified":21,"n_samples":58,"n_pointer_only_licence":4,"sample_list":"/paper/llama-open-and-efficient-foundation-language-1#ran","syntology_url":"https://syntology.ai/paper/2302.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13971"}}}},{"rank_in_archive_order":134,"model":"GPT-3 2.7B","metrics":{"Accuracy":"2.9","Parameters (Billions)":"2.7"},"uses_additional_data":false,"paper_date":"2021-03-05","paper":"/paper/measuring-mathematical-problem-solving-with","paper_url":"https://arxiv.org/abs/2103.03874v2","paper_title":"Measuring Mathematical Problem Solving With the MATH Dataset","code":"https://github.com/hendrycks/math","n_code_links":5,"official":{"repos":["hendrycks/math"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":1,"sample_list":"/paper/measuring-mathematical-problem-solving-with#ran","syntology_url":"https://syntology.ai/paper/2103.03874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.03874"}}}},{"rank_in_archive_order":135,"model":"PaLM 8B","metrics":{"Accuracy":"1.5","Parameters (Billions)":"8"},"uses_additional_data":false,"paper_date":"2022-06-29","paper":"/paper/solving-quantitative-reasoning-problems-with","paper_url":"https://arxiv.org/abs/2206.14858v2","paper_title":"Solving Quantitative Reasoning Problems with Language Models","code":"https://github.com/gair-nlp/abel","n_code_links":1,"official":null,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"adjudicator":"Claude Opus 5.5","adjudicator_from":"groundwork/59_code_with_papers/LB_EXTRACTOR_PREREG.md (not recorded in lb_measurement.json; the file's frozen_commit, measured_on and counts equal the run the pre-registration records)","adjudicator_sensitivity":[69,70],"adjudicator_specificity":[101,103],"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication by a model (adjudicator) of accepted entries on a held-out split of archive papers, rules frozen before the test; adjudicator_sensitivity and adjudicator_specificity are its own controls as [judged right, of]; it was not measured on the newer papers placed here","measurement_sentence":"Measured before publishing, on held-out archive papers: the extractor was given 883 of them and produced output for 881 (the other 2 had no title and were excluded before any model call, so they are not part of this measurement). A model adjudicator (Claude Opus 5.5), blind to which entries were real, judged 108 of 110 accepted entries correct on those held-out archive papers; its own controls: 69 of 70 archive-confirmed entries judged true, 101 of 103 corrupted copies judged false. It was not measured on the newer papers whose results are placed on this site.","coverage":{"sentence":"Syntology has checked 8,886 of the 18,637 papers on this site that are newer than the archive (for 3,717 of them no archive leaderboard matched the paper's tables, so there was nothing further to check); 733 were read and have nothing to place (arXiv has no HTML version of the paper, or that version has no tables), 41 could not be read (the extractor's reply could not be parsed), and results from the other 8,977 appear after they are checked.","complete":false,"papers_newer_than_archive":18637,"papers_checked":8886,"papers_checked_no_leaderboard_matched":3717,"papers_read_nothing_to_place":733,"papers_could_not_be_read":41,"papers_could_not_be_read_by_status":{"unparseable":41},"papers_extracted_not_yet_verified":0,"boards_without_verdict":3,"papers_not_yet_extracted":8975},"board_status":{"sentence":"Of the 8,888 newer papers whose tables Syntology has read (8,886 checked in full and 2 with a leaderboard still awaiting a verdict), 152 had this board among the leaderboards the extractor considered for their tables (it keeps at most 10 boards per paper and 4 per dataset; the lists of 1,522 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and 53 proposed a result; of those 53, 38 gave no cell that passed the extractor's own checks, 15 were rejected by the independent check, 0 await a verdict and 0 were placed.","note":"papers, from the extractor's own records, over the newer papers whose tables were read; proposed = no_cell_passed_checks + rejected_by_independent_check + accepted_not_placed + awaiting_verdict + placed; counts, never a rate","eligible":true,"eligible_note":"false when the extractor never considers this board: it loads only boards with archive rows and at least one metric column (lb_extract.py Boards), so no newer paper can be proposed here; archive_rows and metric_columns say which","archive_rows":135,"metric_columns":2,"papers_read":8888,"papers_read_checked":8886,"papers_read_awaiting_verdict":2,"papers_read_verified":8888,"papers_read_not_yet_verified":0,"papers_read_at_candidate_cap":1596,"papers_read_list_full_without_this_board":1522,"candidates":152,"candidates_capped_note":"candidates = papers that had this board among the leaderboards the extractor considered for their tables; the extractor keeps at most 10 per paper and 4 per dataset, so a board crowded out of a paper's list is not counted and candidates is a floor; papers_read_list_full_without_this_board counts the read papers whose list did not hold this board and had reached 10, or held 4 boards of this board's dataset (the only papers that could have crowded it out); papers_read_at_candidate_cap counts, over every board, the papers whose list reached 10","proposed":53,"no_cell_passed_checks":38,"rejected_by_independent_check":15,"accepted_not_placed":0,"awaiting_verdict":0,"placed":0,"placed_entries_listed":0,"file_lines_unreadable_as_read":0,"since_line":"Since the archive (Syntology): none placed; 53 newer papers judged to report on this board so far"},"judged_to_report":{"heading":"Newer papers whose tables Claude Sonnet 4.5 judged to report on this benchmark (a model's judgement, not a result; newest first by arXiv id)","judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"a_record_without_a_model":false,"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here","order":"newest first by arXiv id (the identifier's order, not a rank)","outcomes":{"placed":"placed","no_cell_passed_checks":"no cell passed the extractor's checks","refused_by_rule":"refused by a rule","rejected":"rejected by the independent check","accepted_not_placed":"accepted by the independent check but not placed by this site","awaiting":"awaiting a verdict"},"reason_note":"for refused_by_rule, the rules' plain words for the reason codes the record gives (never the quoted or the actual cell text); null for every other outcome","total":53,"shown_on_page":53,"no_cell_split":{"no_cell_passed_checks_in_ledger":38,"rows_refused_by_rule":38,"rows_no_cell_passed_checks":0},"rows":[{"arxiv_id":"2609.00791","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2608.26550","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2608.09542","outcome":"rejected","reason":null},{"arxiv_id":"2607.16252","outcome":"rejected","reason":null},{"arxiv_id":"2607.13394","outcome":"refused_by_rule","reason":"the number the model quoted is not the number printed in the cell it pointed at"},{"arxiv_id":"2606.09052","outcome":"refused_by_rule","reason":"the number the model quoted is not the number printed in the cell it pointed at"},{"arxiv_id":"2606.08728","outcome":"refused_by_rule","reason":"the model pointed at a header row; the row label the model quoted is not the row's label; the table, row or column pointed at does not exist"},{"arxiv_id":"2606.07108","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2606.05859","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2606.04974","outcome":"rejected","reason":null},{"arxiv_id":"2606.04964","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2606.01041","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2606.00869","outcome":"rejected","reason":null},{"arxiv_id":"2605.30712","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2605.29398","outcome":"refused_by_rule","reason":"the row is an ablation variant, not the method itself"},{"arxiv_id":"2605.25198","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2605.22939","outcome":"rejected","reason":null},{"arxiv_id":"2605.22869","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2605.20722","outcome":"rejected","reason":null},{"arxiv_id":"2605.17672","outcome":"rejected","reason":null},{"arxiv_id":"2605.17104","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2605.13647","outcome":"rejected","reason":null},{"arxiv_id":"2605.08936","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2605.07315","outcome":"rejected","reason":null},{"arxiv_id":"2605.00195","outcome":"refused_by_rule","reason":"the model pointed at a header row"},{"arxiv_id":"2604.25444","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2604.23626","outcome":"rejected","reason":null},{"arxiv_id":"2604.13552","outcome":"rejected","reason":null},{"arxiv_id":"2604.03616","outcome":"rejected","reason":null},{"arxiv_id":"2603.20215","outcome":"refused_by_rule","reason":"the number the model quoted is not the number printed in the cell it pointed at"},{"arxiv_id":"2603.18533","outcome":"rejected","reason":null},{"arxiv_id":"2603.07079","outcome":"rejected","reason":null},{"arxiv_id":"2603.06859","outcome":"refused_by_rule","reason":"the row is an ablation variant, not the method itself"},{"arxiv_id":"2602.23225","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric; the quoted value appears more than once in the row"},{"arxiv_id":"2602.22480","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric; the row is an ablation variant, not the method itself"},{"arxiv_id":"2602.12222","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2602.10693","outcome":"refused_by_rule","reason":"the table does not name the leaderboard's dataset"},{"arxiv_id":"2602.06600","outcome":"refused_by_rule","reason":"the row is an ablation variant, not the method itself"},{"arxiv_id":"2602.06462","outcome":"refused_by_rule","reason":"the row label the model quoted is not the row's label"},{"arxiv_id":"2602.01982","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2601.23184","outcome":"refused_by_rule","reason":"the number the model quoted is not the number printed in the cell it pointed at"},{"arxiv_id":"2601.21484","outcome":"refused_by_rule","reason":"the table does not name the leaderboard's dataset"},{"arxiv_id":"2601.18533","outcome":"refused_by_rule","reason":"the row label the model quoted is not the row's label"},{"arxiv_id":"2601.07372","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2601.04700","outcome":"refused_by_rule","reason":"the row label the model quoted is not the row's label"},{"arxiv_id":"2512.14681","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2512.11391","outcome":"refused_by_rule","reason":"the row is an ablation variant, not the method itself"},{"arxiv_id":"2512.05542","outcome":"refused_by_rule","reason":"the number the model quoted is not the number printed in the cell it pointed at"},{"arxiv_id":"2511.18760","outcome":"rejected","reason":null},{"arxiv_id":"2510.07312","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2510.06672","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2510.04019","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2509.24945","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"}]},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per row: of M harvested code samples from that row's paper, n_ran executed on a synthesized fixture (n_ran = n_ran_checked + n_instrument; n_instrument counts failures of Syntology's instrument, not of the code); the other M - n_ran are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"rows_with_graph_line":76,"rows_with_any_sample_ran":73,"rows_with_a_run_with_no_instrument_failure":57,"official":{"state_rule":"the archive's official repositories have samples for this paper that ran: 'official (archive's flag): N ran' (N counts them, instrument failures included); they have samples, none ran: 'official: harvested, nothing ran'; they have no sample for this paper and another sample ran: 'community repositories only' when every sample that ran came from a repository the archive lists for the paper but neither marks official nor records as mentioned in it, or one Syntology harvested outside the archive's links, else 'official: no sample here; runs from other or unrecorded repositories' (a repository named in the paper or found in its text by Syntology, or no repository recorded); otherwise 'official: harvested for another paper' or 'official: not harvested'. Absent when the archive marks no repository official. Official is the archive's is_official flag, not an authorship verdict","flag":"the archive's is_official flag for the paper's code link; not a verdict on who wrote the code","rows_with_an_archive_official_repository":64,"rows_whose_official_repository_has_a_sample_that_ran":53,"rows_whose_official_repository_has_a_run_with_no_instrument_failure":38,"rows_community_repositories_only":0,"rows_runs_from_other_or_unrecorded_repositories":8,"note":"rows[].official, per row with a graph line: repos (marked official in the archive), state, n_ran and n_unverified (samples from those repositories), and ran_from_kinds (the kinds of repository the paper's samples that ran came from; 'unlocated' is no repository recorded)"},"filters":{"ran_modes":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"the page's filters hide rows and never renumber them; they read the Ran cell's counts, the same figures rows[].syntology and rows[].official carry"},"row_route":"rows[].syntology carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","distinct_papers_with_graph_line":22,"distinct_papers_with_any_sample_ran":20,"distinct_papers_with_a_run_with_no_instrument_failure":16,"samples_over_distinct_papers":{"n_ran":189,"n_constructed":15,"n_ran_checked":94,"n_instrument":95,"n_unverified":63,"n_samples":252,"n_pointer_only_licence":91,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":785,"n_constructed":83,"n_ran_checked":394,"n_instrument":391,"n_unverified":290,"n_samples":1075,"n_pointer_only_licence":279,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}},"record_sha256":"b17075a283fe398ca935638180d7c1441fd5193879c7f593beccb1668eb91a8c","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}