{"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/arithmetic-reasoning-on-gsm8k","task":{"name":"Arithmetic Reasoning","url":"/task/arithmetic-reasoning","note":null},"dataset":{"name":"GSM8K","url":"/dataset/gsm8k"},"category":"Reasoning","categories":["Reasoning"],"category_note":null,"description":null,"description_from":null,"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 (Billion)"],"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 (Billion)":null}},"counts":{"rows":164,"rows_with_code":118,"rows_with_paper_page":150,"rows_dated":150,"rows_using_additional_data":85},"rows":[{"rank_in_archive_order":1,"model":"Claude 3.5 Sonnet (HPT)","metrics":{"Accuracy":"97.72"},"uses_additional_data":false,"paper_date":"2024-06-18","paper":"/paper/hierarchical-prompting-taxonomy-a-universal","paper_url":"https://arxiv.org/abs/2406.12644v4","paper_title":"Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models Aligned with Human Cognitive Principles","code":"https://github.com/devichand579/HPT","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":2,"model":"DUP prompt upon GPT-4","metrics":{"Accuracy":"97.1"},"uses_additional_data":false,"paper_date":"2024-04-23","paper":"/paper/achieving-97-on-gsm8k-deeply-understanding","paper_url":"https://arxiv.org/abs/2404.14963v5","paper_title":"Achieving >97% on GSM8K: Deeply Understanding the Problems Makes LLMs Better Solvers for Math Word Problems","code":"https://github.com/whu-zqh/dup","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":3,"model":"Qwen2-Math-72B-Instruct\n(greedy)","metrics":{"Accuracy":"96.7","Parameters (Billion)":"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":4,"model":"SFT-Mistral-7B (Metamath, OVM, Smart Ensemble)","metrics":{"Accuracy":"96.4","Parameters (Billion)":"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":5,"model":"OpenMath2-Llama3.1-70B (majority@256)","metrics":{"Accuracy":"96.0"},"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":6,"model":"Jiutian-大模型","metrics":{"Accuracy":"95.2","Parameters (Billion)":"75"},"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":7,"model":"DAMOMath-7B(MetaMath, OVM, BS, Ensemble)","metrics":{"Accuracy":"95.1","Parameters (Billion)":"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":8,"model":"Claude 3 Opus (0-shot chain-of-thought)","metrics":{"Accuracy":"95"},"uses_additional_data":false,"paper_date":"2024-03-04","paper":"/paper/the-claude-3-model-family-opus-sonnet-haiku","paper_url":"https://www.anthropic.com/news/claude-3-family","paper_title":"The Claude 3 Model Family: Opus, Sonnet, Haiku","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":9,"model":"OpenMath2-Llama3.1-70B","metrics":{"Accuracy":"94.9"},"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":10,"model":"GPT-4 (Teaching-Inspired)","metrics":{"Accuracy":"94.8"},"uses_additional_data":false,"paper_date":"2024-10-10","paper":"/paper/teaching-inspired-integrated-prompting","paper_url":"https://arxiv.org/abs/2410.08068v1","paper_title":"Teaching-Inspired Integrated Prompting Framework: A Novel Approach for Enhancing Reasoning in Large Language Models","code":"https://github.com/sallytan13/teaching-inspired-prompting","n_code_links":1,"official":{"repos":["sallytan13/teaching-inspired-prompting"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":0,"n_samples":8,"n_pointer_only_licence":8,"sample_list":"/paper/teaching-inspired-integrated-prompting#ran","syntology_url":"https://syntology.ai/paper/2410.08068","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08068"}}}},{"rank_in_archive_order":11,"model":"SFT-Mistral-7B (Metamath + ovm +ensemble)","metrics":{"Accuracy":"94.13","Parameters (Billion)":"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":12,"model":"OpenMath2-Llama3.1-8B (majority@256)","metrics":{"Accuracy":"94.1"},"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":13,"model":"Qwen2-72B-Instruct-Step-DPO (0-shot CoT)","metrics":{"Accuracy":"94.0"},"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":14,"model":"DAMOMath-7B(MetaMath, OVM, Ensemble)","metrics":{"Accuracy":"93.2","Parameters (Billion)":"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":15,"model":"Claude 3 Sonnet (0-shot chain-of-thought)","metrics":{"Accuracy":"92.3"},"uses_additional_data":false,"paper_date":"2024-03-04","paper":"/paper/the-claude-3-model-family-opus-sonnet-haiku","paper_url":"https://www.anthropic.com/news/claude-3-family","paper_title":"The Claude 3 Model Family: Opus, Sonnet, Haiku","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":16,"model":"AlphaLLM (with MCTS)","metrics":{"Accuracy":"92","Parameters (Billion)":"70"},"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":17,"model":"OpenMath2-Llama3.1-8B","metrics":{"Accuracy":"91.7"},"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":18,"model":"PaLM 2 (few-shot, k=8, SC)","metrics":{"Accuracy":"91.0"},"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":19,"model":"GaC(Qwen2-72B-Instruct + Llama-3-70B-Instruct)","metrics":{"Accuracy":"90.91"},"uses_additional_data":false,"paper_date":"2024-06-18","paper":"/paper/breaking-the-ceiling-of-the-llm-community-by","paper_url":"https://arxiv.org/abs/2406.12585v2","paper_title":"Breaking the Ceiling of the LLM Community by Treating Token Generation as a Classification for Ensembling","code":"https://github.com/yaoching0/gac","n_code_links":1,"official":{"repos":["yaoching0/gac"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_samples":7,"n_pointer_only_licence":1,"sample_list":"/paper/breaking-the-ceiling-of-the-llm-community-by#ran","syntology_url":"https://syntology.ai/paper/2406.12585","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12585"}}}},{"rank_in_archive_order":20,"model":"OpenMath-CodeLlama-70B (w/ code, SC, k=50)","metrics":{"Accuracy":"90.8","Parameters (Billion)":"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":21,"model":"DART-Math-Llama3-70B-Uniform (0-shot CoT, w/o code)","metrics":{"Accuracy":"90.4","Parameters (Billion)":"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":22,"model":"OpenMath-Llama2-70B (w/ code, SC, k=50)","metrics":{"Accuracy":"90.1","Parameters (Billion)":"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":23,"model":"DART-Math-Llama3-70B-Prop2Diff (0-shot CoT, w/o code)","metrics":{"Accuracy":"89.6","Parameters (Billion)":"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":24,"model":"Shepherd+Mistral-7B (SFT on MetaMATH + PRM RL+ PRM rerank, k=256)","metrics":{"Accuracy":"89.1","Parameters (Billion)":"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":25,"model":"Llama SFT (Metamath ToRA Ensemble)","metrics":{"Accuracy":"89.0","Parameters (Billion)":"13"},"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":26,"model":"Minerva 62B (maj5@100)","metrics":{"Accuracy":"89","Parameters (Billion)":"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":27,"model":"Claude 3 Haiku (0-shot chain-of-thought)","metrics":{"Accuracy":"88.9"},"uses_additional_data":false,"paper_date":"2024-03-04","paper":"/paper/the-claude-3-model-family-opus-sonnet-haiku","paper_url":"https://www.anthropic.com/news/claude-3-family","paper_title":"The Claude 3 Model Family: Opus, Sonnet, Haiku","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":28,"model":"ToRA-70B (SC, k=50)","metrics":{"Accuracy":"88.3","Parameters (Billion)":"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":29,"model":"DeepSeekMATH-RL-7B","metrics":{"Accuracy":"88.2","Parameters (Billion)":"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":30,"model":"DART-Math-DSMath-7B-Uniform (0-shot CoT, w/o code)","metrics":{"Accuracy":"88.2","Parameters (Billion)":"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":31,"model":"OpenMath-CodeLlama-34B (w/ code, SC, k=50)","metrics":{"Accuracy":"88.0","Parameters (Billion)":"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":32,"model":"Claude 2 (0-shot chain-of-thought)","metrics":{"Accuracy":"88"},"uses_additional_data":false,"paper_date":"2023-07-11","paper":"/paper/model-card-and-evaluations-for-claude-models","paper_url":"https://www-files.anthropic.com/production/images/Model-Card-Claude-2.pdf","paper_title":"Model Card and Evaluations for Claude Models","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":33,"model":"Shivaay-4B (8-shot chain-of-thought)","metrics":{"Accuracy":"87.41","Parameters (Billion)":"4"},"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":34,"model":"DeepMind 70B Model (SFT+ORM-RL, ORM reranking)","metrics":{"Accuracy":"87.3","Parameters (Billion)":"70"},"uses_additional_data":true,"paper_date":"2022-11-25","paper":"/paper/solving-math-word-problems-with-process-and","paper_url":"https://arxiv.org/abs/2211.14275v1","paper_title":"Solving math word problems with process- and outcome-based feedback","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":35,"model":"MMOS-DeepSeekMath-7B(0-shot,k=50)","metrics":{"Accuracy":"87.2","Parameters (Billion)":"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":36,"model":"DeepMind 70B Model (SFT+PRM-RL, PRM reranking)","metrics":{"Accuracy":"87.1","Parameters (Billion)":"70"},"uses_additional_data":true,"paper_date":"2022-11-25","paper":"/paper/solving-math-word-problems-with-process-and","paper_url":"https://arxiv.org/abs/2211.14275v1","paper_title":"Solving math word problems with process- and outcome-based feedback","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":37,"model":"GPT-4","metrics":{"Accuracy":"87.1"},"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":38,"model":"OpenMath-Mistral-7B (w/ code, SC, k=50)","metrics":{"Accuracy":"86.9","Parameters (Billion)":"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":39,"model":"Orca-Math 7B (fine-tuned)","metrics":{"Accuracy":"86.8","Parameters (Billion)":"7"},"uses_additional_data":true,"paper_date":"2024-02-16","paper":"/paper/orca-math-unlocking-the-potential-of-slms-in","paper_url":"https://arxiv.org/abs/2402.14830v1","paper_title":"Orca-Math: Unlocking the potential of SLMs in Grade School Math","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":40,"model":"DART-Math-DSMath-7B-Prop2Diff (0-shot CoT, w/o code)","metrics":{"Accuracy":"86.8","Parameters (Billion)":"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":"OpenMath-CodeLlama-13B (w/ code, SC, k=50)","metrics":{"Accuracy":"86.8","Parameters (Billion)":"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":42,"model":"Gemini Pro (maj1@32)","metrics":{"Accuracy":"86.5"},"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":43,"model":"Codex (Self-Evaluation Guided Decoding, PAL, multiple reasoning chains, 9-shot gen, 5-shot eval)","metrics":{"Accuracy":"85.5"},"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":44,"model":"Claude 1.3 (0-shot chain-of-thought)","metrics":{"Accuracy":"85.2"},"uses_additional_data":false,"paper_date":"2023-07-11","paper":"/paper/model-card-and-evaluations-for-claude-models","paper_url":"https://www-files.anthropic.com/production/images/Model-Card-Claude-2.pdf","paper_title":"Model Card and Evaluations for Claude Models","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":45,"model":"ToRA-Code-34B (SC, k=50)","metrics":{"Accuracy":"85.1","Parameters (Billion)":"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":46,"model":"OpenMath-CodeLlama-7B (w/ code, SC, k=50)","metrics":{"Accuracy":"84.8","Parameters (Billion)":"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":47,"model":"OVM-Mistral-7B (verify100@1)","metrics":{"Accuracy":"84.7","Parameters (Billion)":"7"},"uses_additional_data":false,"paper_date":"2023-11-16","paper":"/paper/outcome-supervised-verifiers-for-planning-in","paper_url":"https://arxiv.org/abs/2311.09724v2","paper_title":"OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoning","code":"https://github.com/freedomintelligence/ovm","n_code_links":1,"official":{"repos":["freedomintelligence/ovm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3,"sample_list":"/paper/outcome-supervised-verifiers-for-planning-in#ran","syntology_url":"https://syntology.ai/paper/2311.09724","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09724"}}}},{"rank_in_archive_order":48,"model":"OpenMath-Llama2-70B (w/ code)","metrics":{"Accuracy":"84.7","Parameters (Billion)":"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":49,"model":"OpenMath-CodeLlama-70B (w/ code)","metrics":{"Accuracy":"84.6","Parameters (Billion)":"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":50,"model":"code-davinci-002 175B (LEVER, 8-shot)","metrics":{"Accuracy":"84.5","Parameters (Billion)":"175"},"uses_additional_data":false,"paper_date":"2023-02-16","paper":"/paper/lever-learning-to-verify-language-to-code","paper_url":"https://arxiv.org/abs/2302.08468v3","paper_title":"LEVER: Learning to Verify Language-to-Code Generation with Execution","code":"https://github.com/niansong1996/lever","n_code_links":1,"official":{"repos":["niansong1996/lever"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":4,"ran_from_kinds":["official"]},"syntology":{"n_ran":18,"n_constructed":0,"n_ran_checked":14,"n_instrument":4,"n_unverified":4,"n_samples":22,"n_pointer_only_licence":1,"sample_list":"/paper/lever-learning-to-verify-language-to-code#ran","syntology_url":"https://syntology.ai/paper/2302.08468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.08468"}}}},{"rank_in_archive_order":51,"model":"ToRA 70B","metrics":{"Accuracy":"84.3","Parameters (Billion)":"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":52,"model":"Shepherd + Mistral-7B (SFT on MetaMATH + PRM RL)","metrics":{"Accuracy":"84.1","Parameters (Billion)":"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":53,"model":"MathCoder-L-70B","metrics":{"Accuracy":"83.9","Parameters (Billion)":"70"},"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":54,"model":"WizardMath-7B-V1.1","metrics":{"Accuracy":"83.2","Parameters (Billion)":"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":55,"model":"DIVERSE 175B (8-shot)","metrics":{"Accuracy":"83.2","Parameters (Billion)":"175"},"uses_additional_data":false,"paper_date":"2022-06-06","paper":"/paper/on-the-advance-of-making-language-models","paper_url":"https://arxiv.org/abs/2206.02336v3","paper_title":"Making Large Language Models Better Reasoners with Step-Aware Verifier","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":56,"model":"OVM-Mistral-7B (verify20@1)","metrics":{"Accuracy":"82.6","Parameters (Billion)":"7"},"uses_additional_data":false,"paper_date":"2023-11-16","paper":"/paper/outcome-supervised-verifiers-for-planning-in","paper_url":"https://arxiv.org/abs/2311.09724v2","paper_title":"OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoning","code":"https://github.com/freedomintelligence/ovm","n_code_links":1,"official":{"repos":["freedomintelligence/ovm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3,"sample_list":"/paper/outcome-supervised-verifiers-for-planning-in#ran","syntology_url":"https://syntology.ai/paper/2311.09724","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09724"}}}},{"rank_in_archive_order":57,"model":"DART-Math-Mistral-7B-Uniform (0-shot CoT, w/o code)","metrics":{"Accuracy":"82.6","Parameters (Billion)":"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":58,"model":"ChatGPT (Ask, Refine, Trust)","metrics":{"Accuracy":"82.6"},"uses_additional_data":false,"paper_date":"2023-11-14","paper":"/paper/the-art-of-llm-refinement-ask-refine-and","paper_url":"https://arxiv.org/abs/2311.07961v1","paper_title":"The ART of LLM Refinement: Ask, Refine, and Trust","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":59,"model":"DART-Math-Llama3-8B-Uniform (0-shot CoT, w/o code)","metrics":{"Accuracy":"82.5","Parameters (Billion)":"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":"MetaMath 70B","metrics":{"Accuracy":"82.3","Parameters (Billion)":"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":61,"model":"MuggleMATH 70B","metrics":{"Accuracy":"82.3","Parameters (Billion)":"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":62,"model":"PaLM 540B (Self Improvement, Self Consistency)","metrics":{"Accuracy":"82.1","Parameters (Billion)":"540"},"uses_additional_data":false,"paper_date":"2022-10-20","paper":"/paper/large-language-models-can-self-improve","paper_url":"https://arxiv.org/abs/2210.11610v2","paper_title":"Large Language Models Can Self-Improve","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":63,"model":"MathCoder-CL-34B","metrics":{"Accuracy":"81.7","Parameters (Billion)":"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":64,"model":"WizardMath-70B-V1.0","metrics":{"Accuracy":"81.6","Parameters (Billion)":"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":65,"model":"Phi-GSM+V 1.3B+1.3B (verify48@1)","metrics":{"Accuracy":"81.5","Parameters (Billion)":"2.6"},"uses_additional_data":false,"paper_date":"2023-12-14","paper":"/paper/tinygsm-achieving-80-on-gsm8k-with-small","paper_url":"https://arxiv.org/abs/2312.09241v1","paper_title":"TinyGSM: achieving >80% on GSM8k with small language models","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":66,"model":"DART-Math-Mistral-7B-Prop2Diff (0-shot CoT, w/o code)","metrics":{"Accuracy":"81.1","Parameters (Billion)":"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":67,"model":"DART-Math-Llama3-8B-Prop2Diff (0-shot CoT, w/o code)","metrics":{"Accuracy":"81.1","Parameters (Billion)":"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":68,"model":"Claude Instant 1.1 (0-shot chain-of-thought)","metrics":{"Accuracy":"80.9"},"uses_additional_data":false,"paper_date":"2023-07-11","paper":"/paper/model-card-and-evaluations-for-claude-models","paper_url":"https://www-files.anthropic.com/production/images/Model-Card-Claude-2.pdf","paper_title":"Model Card and Evaluations for Claude Models","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":69,"model":"ToRA-Code 34B","metrics":{"Accuracy":"80.7","Parameters (Billion)":"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":70,"model":"OpenMath-CodeLlama-34B (w/ code)","metrics":{"Accuracy":"80.7","Parameters (Billion)":"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":71,"model":"PaLM 2 (few-shot, k=8, CoT)","metrics":{"Accuracy":"80.7"},"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":72,"model":"MMOS-DeepSeekMath-7B(0-shot)","metrics":{"Accuracy":"80.5","Parameters (Billion)":"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":73,"model":"MMOS-CODE-34B(0-shot)","metrics":{"Accuracy":"80.4","Parameters (Billion)":"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":74,"model":"OpenMath-Mistral-7B (w/ code)","metrics":{"Accuracy":"80.2","Parameters (Billion)":"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":75,"model":"Self-Evaluation Guided Decoding (Codex, PAL, single reasoning chain, 9-shot gen, 5-shot eval)","metrics":{"Accuracy":"80.2"},"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":76,"model":"OpenMath-CodeLlama-13B (w/ code)","metrics":{"Accuracy":"78.8","Parameters (Billion)":"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":77,"model":"Minerva 540B (CoT)","metrics":{"Accuracy":"78.5","Parameters (Billion)":"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":78,"model":"Camelidae-8×34B (5-shot)","metrics":{"Accuracy":"78.3"},"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":79,"model":"Qwen2idae-16x14B (5-shot)","metrics":{"Accuracy":"77.8"},"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":80,"model":"MetaMath-Mistral-7B","metrics":{"Accuracy":"77.7","Parameters (Billion)":"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":81,"model":"OpenChat-3.5 7B","metrics":{"Accuracy":"77.3","Parameters (Billion)":"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":82,"model":"DeepMind 70B Model (STaR, maj1@96)","metrics":{"Accuracy":"76.5","Parameters (Billion)":"70"},"uses_additional_data":true,"paper_date":"2022-11-25","paper":"/paper/solving-math-word-problems-with-process-and","paper_url":"https://arxiv.org/abs/2211.14275v1","paper_title":"Solving math word problems with process- and outcome-based feedback","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":83,"model":"Arithmo2-Mistral-7B","metrics":{"Accuracy":"76.4","Parameters (Billion)":"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":84,"model":"OpenMath-CodeLlama-7B (w/ code)","metrics":{"Accuracy":"75.9","Parameters (Billion)":"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":85,"model":"ToRA-Code 13B","metrics":{"Accuracy":"75.8","Parameters (Billion)":"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":86,"model":"Arithmo-Mistral-7B","metrics":{"Accuracy":"74.7","Parameters (Billion)":"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":87,"model":"PaLM 540B maj1@40 (8-shot)","metrics":{"Accuracy":"74.4","Parameters (Billion)":"540"},"uses_additional_data":true,"paper_date":"2022-03-21","paper":"/paper/self-consistency-improves-chain-of-thought","paper_url":"https://arxiv.org/abs/2203.11171v4","paper_title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","code":"https://github.com/codelion/optillm/blob/main/optillm/self_consistency.py","n_code_links":3,"official":null,"syntology":{"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/self-consistency-improves-chain-of-thought#ran","syntology_url":"https://syntology.ai/paper/2203.11171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.11171"}}}},{"rank_in_archive_order":88,"model":"PaLM 540B (Self Consistency)","metrics":{"Accuracy":"74.4","Parameters (Billion)":"540"},"uses_additional_data":false,"paper_date":"2022-10-20","paper":"/paper/large-language-models-can-self-improve","paper_url":"https://arxiv.org/abs/2210.11610v2","paper_title":"Large Language Models Can Self-Improve","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":89,"model":"Phi-GSM 2.7B (fine-tuned)","metrics":{"Accuracy":"74.3","Parameters (Billion)":"2.7"},"uses_additional_data":false,"paper_date":"2023-12-14","paper":"/paper/tinygsm-achieving-80-on-gsm8k-with-small","paper_url":"https://arxiv.org/abs/2312.09241v1","paper_title":"TinyGSM: achieving >80% on GSM8k with small language models","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":90,"model":"MathCoder-CL-13B","metrics":{"Accuracy":"74.1","Parameters (Billion)":"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":91,"model":"MuggleMATH 13B","metrics":{"Accuracy":"74","Parameters (Billion)":"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":92,"model":"MMOS-CODE-7B(0-shot)","metrics":{"Accuracy":"73.9","Parameters (Billion)":"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":93,"model":"CodeT5+","metrics":{"Accuracy":"73.8","Parameters (Billion)":"0.77"},"uses_additional_data":false,"paper_date":"2023-05-13","paper":"/paper/codet5-open-code-large-language-models-for","paper_url":"https://arxiv.org/abs/2305.07922v2","paper_title":"CodeT5+: Open Code Large Language Models for Code Understanding and Generation","code":"https://github.com/salesforce/codet5","n_code_links":2,"official":{"repos":["salesforce/codet5"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0,"sample_list":"/paper/codet5-open-code-large-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2305.07922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.07922"}}}},{"rank_in_archive_order":94,"model":"Llama-3.3-70B + CAPO","metrics":{"Accuracy":"73.73"},"uses_additional_data":false,"paper_date":"2025-04-22","paper":"/paper/capo-cost-aware-prompt-optimization","paper_url":"https://arxiv.org/abs/2504.16005v3","paper_title":"CAPO: Cost-Aware Prompt Optimization","code":"https://github.com/finitearth/promptolution","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":95,"model":"OVM-Llama2-7B (verify100@1)","metrics":{"Accuracy":"73.7","Parameters (Billion)":"7"},"uses_additional_data":false,"paper_date":"2023-11-16","paper":"/paper/outcome-supervised-verifiers-for-planning-in","paper_url":"https://arxiv.org/abs/2311.09724v2","paper_title":"OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoning","code":"https://github.com/freedomintelligence/ovm","n_code_links":1,"official":{"repos":["freedomintelligence/ovm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3,"sample_list":"/paper/outcome-supervised-verifiers-for-planning-in#ran","syntology_url":"https://syntology.ai/paper/2311.09724","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.09724"}}}},{"rank_in_archive_order":96,"model":"PaLM 540B (Self Improvement, CoT Prompting)","metrics":{"Accuracy":"73.5","Parameters (Billion)":"540"},"uses_additional_data":false,"paper_date":"2022-10-20","paper":"/paper/large-language-models-can-self-improve","paper_url":"https://arxiv.org/abs/2210.11610v2","paper_title":"Large Language Models Can Self-Improve","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":97,"model":"KwaiYiiMath 13B","metrics":{"Accuracy":"73.3","Parameters (Billion)":"13"},"uses_additional_data":true,"paper_date":"2023-10-11","paper":"/paper/kwaiyiimath-technical-report","paper_url":"https://arxiv.org/abs/2310.07488v2","paper_title":"KwaiYiiMath: Technical Report","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":98,"model":"ToRA-Code 7B","metrics":{"Accuracy":"72.6","Parameters (Billion)":"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":99,"model":"MathCoder-L-13B","metrics":{"Accuracy":"72.6","Parameters (Billion)":"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":100,"model":"DBRX Base 132B","metrics":{"Accuracy":"72.3"},"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":101,"model":"Self-Evaluation Guided Decoding (Codex, CoT, single reasoning chain, 9-shot gen, 5-shot eval)","metrics":{"Accuracy":"71.9"},"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":102,"model":"MetaMath 13B","metrics":{"Accuracy":"71.0","Parameters (Billion)":"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":103,"model":"MuggleMATH 7B","metrics":{"Accuracy":"69.8","Parameters (Billion)":"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":104,"model":"LLaMA 65B-maj1@k","metrics":{"Accuracy":"69.7","Parameters (Billion)":"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":105,"model":"Minerva 62B (maj1@100)","metrics":{"Accuracy":"68.5","Parameters (Billion)":"62"},"uses_additional_data":true,"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":"code-davinci-002 (Least-to-Most Prompting)","metrics":{"Accuracy":"68.01","Parameters (Billion)":"175"},"uses_additional_data":false,"paper_date":"2022-05-21","paper":"/paper/least-to-most-prompting-enables-complex","paper_url":"https://arxiv.org/abs/2205.10625v3","paper_title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","code":"https://github.com/RUCAIBox/LLMBox","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":107,"model":"MathCoder-CL-7B","metrics":{"Accuracy":"67.8","Parameters (Billion)":"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":108,"model":"DBRX Instruct 132B","metrics":{"Accuracy":"66.9"},"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":109,"model":"MetaMath 7B","metrics":{"Accuracy":"66.4","Parameters (Billion)":"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":110,"model":"Mistral-Small-24B + CAPO","metrics":{"Accuracy":"65.07"},"uses_additional_data":false,"paper_date":"2025-04-22","paper":"/paper/capo-cost-aware-prompt-optimization","paper_url":"https://arxiv.org/abs/2504.16005v3","paper_title":"CAPO: Cost-Aware Prompt Optimization","code":"https://github.com/finitearth/promptolution","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":111,"model":"RFT 70B","metrics":{"Accuracy":"64.8","Parameters (Billion)":"79"},"uses_additional_data":true,"paper_date":"2023-08-03","paper":"/paper/scaling-relationship-on-learning-mathematical","paper_url":"https://arxiv.org/abs/2308.01825v2","paper_title":"Scaling Relationship on Learning Mathematical Reasoning with Large Language Models","code":"https://github.com/ofa-sys/gsm8k-screl","n_code_links":1,"official":{"repos":["ofa-sys/gsm8k-screl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3,"sample_list":"/paper/scaling-relationship-on-learning-mathematical#ran","syntology_url":"https://syntology.ai/paper/2308.01825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.01825"}}}},{"rank_in_archive_order":112,"model":"MathCoder-L-7B","metrics":{"Accuracy":"64.2","Parameters (Billion)":"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":113,"model":"WizardMath-13B-V1.0","metrics":{"Accuracy":"63.9","Parameters (Billion)":"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":114,"model":"GPT-J (CoRe)","metrics":{"Accuracy":"63.2","Parameters (Billion)":"12"},"uses_additional_data":false,"paper_date":"2022-10-28","paper":"/paper/solving-math-word-problem-via-cooperative","paper_url":"https://arxiv.org/abs/2210.16257v5","paper_title":"Solving Math Word Problems via Cooperative Reasoning induced Language Models","code":"https://github.com/tianhongzxy/core","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":115,"model":"Llama-2 70B (on 100 first questions, 4-shot, auto-optimized prompting)","metrics":{"Accuracy":"61","Parameters (Billion)":"70"},"uses_additional_data":false,"paper_date":"2024-02-09","paper":"/paper/the-unreasonable-effectiveness-of-eccentric","paper_url":"https://arxiv.org/abs/2402.10949v2","paper_title":"The Unreasonable Effectiveness of Eccentric Automatic Prompts","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":116,"model":"Qwen2.5-32B + CAPO","metrics":{"Accuracy":"60.2"},"uses_additional_data":false,"paper_date":"2025-04-22","paper":"/paper/capo-cost-aware-prompt-optimization","paper_url":"https://arxiv.org/abs/2504.16005v3","paper_title":"CAPO: Cost-Aware Prompt Optimization","code":"https://github.com/finitearth/promptolution","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":117,"model":"LLaMA 2 70B (CoT-Influx)","metrics":{"Accuracy":"59.59","Parameters (Billion)":"70"},"uses_additional_data":false,"paper_date":"2023-12-14","paper":"/paper/boosting-llm-reasoning-push-the-limits-of-few","paper_url":"https://arxiv.org/abs/2312.08901v3","paper_title":"Fewer is More: Boosting LLM Reasoning with Reinforced Context Pruning","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":118,"model":"Orca 2 13B","metrics":{"Accuracy":"59.14","Parameters (Billion)":"13"},"uses_additional_data":false,"paper_date":"2023-11-18","paper":"/paper/orca-2-teaching-small-language-models-how-to","paper_url":"https://arxiv.org/abs/2311.11045v2","paper_title":"Orca 2: Teaching Small Language Models How to Reason","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":119,"model":"U-PaLM","metrics":{"Accuracy":"58.5","Parameters (Billion)":"540"},"uses_additional_data":false,"paper_date":"2022-10-20","paper":"/paper/transcending-scaling-laws-with-0-1-extra","paper_url":"https://arxiv.org/abs/2210.11399v2","paper_title":"Transcending Scaling Laws with 0.1% Extra Compute","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":120,"model":"PaLM-540B (few-Shot-cot)","metrics":{"Accuracy":"58.1","Parameters (Billion)":"540"},"uses_additional_data":true,"paper_date":"2022-05-24","paper":"/paper/large-language-models-are-zero-shot-reasoners","paper_url":"https://arxiv.org/abs/2205.11916v4","paper_title":"Large Language Models are Zero-Shot Reasoners","code":"https://github.com/kojima-takeshi188/zero_shot_cot","n_code_links":4,"official":{"repos":["kojima-takeshi188/zero_shot_cot"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":1,"sample_list":"/paper/large-language-models-are-zero-shot-reasoners#ran","syntology_url":"https://syntology.ai/paper/2205.11916","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.11916"}}}},{"rank_in_archive_order":121,"model":"GPT-3.5 (few-shot, k=5)","metrics":{"Accuracy":"57.1"},"uses_additional_data":false,"paper_date":"2023-03-15","paper":"/paper/gpt-4-technical-report-1","paper_url":"https://arxiv.org/abs/2303.08774v5","paper_title":"GPT-4 Technical Report","code":"https://github.com/openai/evals","n_code_links":11,"official":{"repos":["openai/evals"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":1,"sample_list":"/paper/gpt-4-technical-report-1#ran","syntology_url":"https://syntology.ai/paper/2303.08774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08774"}}}},{"rank_in_archive_order":122,"model":"Minerva 8B (maj5@100)","metrics":{"Accuracy":"56.8","Parameters (Billion)":"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":123,"model":"LLaMA 2 70B (on-shot)","metrics":{"Accuracy":"56.8","Parameters (Billion)":"70"},"uses_additional_data":false,"paper_date":"2023-07-18","paper":"/paper/llama-2-open-foundation-and-fine-tuned-chat","paper_url":"https://arxiv.org/abs/2307.09288v2","paper_title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","code":"https://github.com/facebookresearch/llama","n_code_links":19,"official":{"repos":["facebookresearch/llama"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":33,"n_constructed":7,"n_ran_checked":20,"n_instrument":13,"n_unverified":19,"n_samples":52,"n_pointer_only_licence":20,"sample_list":"/paper/llama-2-open-foundation-and-fine-tuned-chat#ran","syntology_url":"https://syntology.ai/paper/2307.09288","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09288"}}}},{"rank_in_archive_order":124,"model":"PaLM 540B (8-shot)","metrics":{"Accuracy":"56.5","Parameters (Billion)":"540"},"uses_additional_data":true,"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":125,"model":"PaLM 540B (CoT Prompting)","metrics":{"Accuracy":"56.5","Parameters (Billion)":"540"},"uses_additional_data":false,"paper_date":"2022-10-20","paper":"/paper/large-language-models-can-self-improve","paper_url":"https://arxiv.org/abs/2210.11610v2","paper_title":"Large Language Models Can Self-Improve","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":126,"model":"RFT 13B","metrics":{"Accuracy":"55.3","Parameters (Billion)":"13"},"uses_additional_data":true,"paper_date":"2023-08-03","paper":"/paper/scaling-relationship-on-learning-mathematical","paper_url":"https://arxiv.org/abs/2308.01825v2","paper_title":"Scaling Relationship on Learning Mathematical Reasoning with Large Language Models","code":"https://github.com/ofa-sys/gsm8k-screl","n_code_links":1,"official":{"repos":["ofa-sys/gsm8k-screl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3,"sample_list":"/paper/scaling-relationship-on-learning-mathematical#ran","syntology_url":"https://syntology.ai/paper/2308.01825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.01825"}}}},{"rank_in_archive_order":127,"model":"Finetuned GPT-3 175B + verifier","metrics":{"Accuracy":"55.0","Parameters (Billion)":"175"},"uses_additional_data":true,"paper_date":"2022-05-24","paper":"/paper/large-language-models-are-zero-shot-reasoners","paper_url":"https://arxiv.org/abs/2205.11916v4","paper_title":"Large Language Models are Zero-Shot Reasoners","code":"https://github.com/kojima-takeshi188/zero_shot_cot","n_code_links":4,"official":{"repos":["kojima-takeshi188/zero_shot_cot"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":1,"sample_list":"/paper/large-language-models-are-zero-shot-reasoners#ran","syntology_url":"https://syntology.ai/paper/2205.11916","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.11916"}}}},{"rank_in_archive_order":128,"model":"WizardMath-7B-V1.0","metrics":{"Accuracy":"54.9","Parameters (Billion)":"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":129,"model":"LLaMA 33B-maj1@k","metrics":{"Accuracy":"53.1","Parameters (Billion)":"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":130,"model":"Minerva 62B (8-shot)","metrics":{"Accuracy":" 52.4","Parameters (Billion)":"62"},"uses_additional_data":true,"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":"Mistral 7B (maj@8)","metrics":{"Accuracy":"52.2","Parameters (Billion)":"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":132,"model":"Llemma 34B","metrics":{"Accuracy":"51.5","Parameters (Billion)":"34"},"uses_additional_data":false,"paper_date":"2023-10-16","paper":"/paper/llemma-an-open-language-model-for-mathematics","paper_url":"https://arxiv.org/abs/2310.10631v3","paper_title":"Llemma: An Open Language Model For Mathematics","code":"https://github.com/eleutherai/gpt-neox","n_code_links":4,"official":{"repos":["EleutherAI/math-lm","eleutherai/gpt-neox","wellecks/llmstep"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_samples":8,"n_pointer_only_licence":0,"sample_list":"/paper/llemma-an-open-language-model-for-mathematics#ran","syntology_url":"https://syntology.ai/paper/2310.10631","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.10631"}}}},{"rank_in_archive_order":133,"model":"Text-davinci-002-175B (zero-plus-few-Shot-cot (8 samples))","metrics":{"Accuracy":"51.5","Parameters (Billion)":"175"},"uses_additional_data":true,"paper_date":"2022-05-24","paper":"/paper/large-language-models-are-zero-shot-reasoners","paper_url":"https://arxiv.org/abs/2205.11916v4","paper_title":"Large Language Models are Zero-Shot Reasoners","code":"https://github.com/kojima-takeshi188/zero_shot_cot","n_code_links":4,"official":{"repos":["kojima-takeshi188/zero_shot_cot"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":1,"sample_list":"/paper/large-language-models-are-zero-shot-reasoners#ran","syntology_url":"https://syntology.ai/paper/2205.11916","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.11916"}}}},{"rank_in_archive_order":134,"model":"RFT 7B","metrics":{"Accuracy":"51.2","Parameters (Billion)":"7"},"uses_additional_data":true,"paper_date":"2023-08-03","paper":"/paper/scaling-relationship-on-learning-mathematical","paper_url":"https://arxiv.org/abs/2308.01825v2","paper_title":"Scaling Relationship on Learning Mathematical Reasoning with Large Language Models","code":"https://github.com/ofa-sys/gsm8k-screl","n_code_links":1,"official":{"repos":["ofa-sys/gsm8k-screl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3,"sample_list":"/paper/scaling-relationship-on-learning-mathematical#ran","syntology_url":"https://syntology.ai/paper/2308.01825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.01825"}}}},{"rank_in_archive_order":135,"model":"LLaMA 65B","metrics":{"Accuracy":"50.9","Parameters (Billion)":"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":136,"model":"Orca 2 7B","metrics":{"Accuracy":"47.23","Parameters (Billion)":"7"},"uses_additional_data":false,"paper_date":"2023-11-18","paper":"/paper/orca-2-teaching-small-language-models-how-to","paper_url":"https://arxiv.org/abs/2311.11045v2","paper_title":"Orca 2: Teaching Small Language Models How to Reason","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":137,"model":"Llama-2 13B (on 100 first questions, 4-shot, auto-optimized prompting)","metrics":{"Accuracy":"43","Parameters (Billion)":"13"},"uses_additional_data":false,"paper_date":"2024-02-09","paper":"/paper/the-unreasonable-effectiveness-of-eccentric","paper_url":"https://arxiv.org/abs/2402.10949v2","paper_title":"The Unreasonable Effectiveness of Eccentric Automatic Prompts","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":138,"model":"text-davinci-002 175B (2-shot, CoT)","metrics":{"Accuracy":"41.3","Parameters (Billion)":"175"},"uses_additional_data":true,"paper_date":"2022-05-24","paper":"/paper/large-language-models-are-zero-shot-reasoners","paper_url":"https://arxiv.org/abs/2205.11916v4","paper_title":"Large Language Models are Zero-Shot Reasoners","code":"https://github.com/kojima-takeshi188/zero_shot_cot","n_code_links":4,"official":{"repos":["kojima-takeshi188/zero_shot_cot"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":1,"sample_list":"/paper/large-language-models-are-zero-shot-reasoners#ran","syntology_url":"https://syntology.ai/paper/2205.11916","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.11916"}}}},{"rank_in_archive_order":139,"model":"Mistral 7B (on 100 first questions, 4-shot, auto-optimized prompting)","metrics":{"Accuracy":"41","Parameters (Billion)":"7"},"uses_additional_data":false,"paper_date":"2024-02-09","paper":"/paper/the-unreasonable-effectiveness-of-eccentric","paper_url":"https://arxiv.org/abs/2402.10949v2","paper_title":"The Unreasonable Effectiveness of Eccentric Automatic Prompts","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":140,"model":"text-davinci-002 175B (0-shot, CoT)","metrics":{"Accuracy":"40.7","Parameters (Billion)":"175"},"uses_additional_data":true,"paper_date":"2022-05-24","paper":"/paper/large-language-models-are-zero-shot-reasoners","paper_url":"https://arxiv.org/abs/2205.11916v4","paper_title":"Large Language Models are Zero-Shot Reasoners","code":"https://github.com/kojima-takeshi188/zero_shot_cot","n_code_links":4,"official":{"repos":["kojima-takeshi188/zero_shot_cot"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":1,"sample_list":"/paper/large-language-models-are-zero-shot-reasoners#ran","syntology_url":"https://syntology.ai/paper/2205.11916","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.11916"}}}},{"rank_in_archive_order":141,"model":"Branch-Train-MiX 4x7B (sampling top-2 experts)","metrics":{"Accuracy":"37.1"},"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":142,"model":"Llemma 7B","metrics":{"Accuracy":"36.4","Parameters (Billion)":"7"},"uses_additional_data":false,"paper_date":"2023-10-16","paper":"/paper/llemma-an-open-language-model-for-mathematics","paper_url":"https://arxiv.org/abs/2310.10631v3","paper_title":"Llemma: An Open Language Model For Mathematics","code":"https://github.com/eleutherai/gpt-neox","n_code_links":4,"official":{"repos":["EleutherAI/math-lm","eleutherai/gpt-neox","wellecks/llmstep"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_samples":8,"n_pointer_only_licence":0,"sample_list":"/paper/llemma-an-open-language-model-for-mathematics#ran","syntology_url":"https://syntology.ai/paper/2310.10631","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.10631"}}}},{"rank_in_archive_order":143,"model":"LLaMA 33B","metrics":{"Accuracy":"35.6","Parameters (Billion)":"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":144,"model":"Vicuna (SYRELM)","metrics":{"Accuracy":"35.2","Parameters (Billion)":"13"},"uses_additional_data":true,"paper_date":"2023-12-09","paper":"/paper/frugal-lms-trained-to-invoke-symbolic-solvers","paper_url":"https://arxiv.org/abs/2312.05571v2","paper_title":"Frugal LMs Trained to Invoke Symbolic Solvers Achieve Parameter-Efficient Arithmetic Reasoning","code":"https://github.com/joykirat18/syrelm","n_code_links":1,"official":{"repos":["joykirat18/syrelm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2,"sample_list":"/paper/frugal-lms-trained-to-invoke-symbolic-solvers#ran","syntology_url":"https://syntology.ai/paper/2312.05571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.05571"}}}},{"rank_in_archive_order":145,"model":"PaLM 62B (8-shot)","metrics":{"Accuracy":"33.0","Parameters (Billion)":"62"},"uses_additional_data":true,"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":146,"model":"PaLM 540B (Self Improvement, Standard-Prompting)","metrics":{"Accuracy":"32.2","Parameters (Billion)":"540"},"uses_additional_data":false,"paper_date":"2022-10-20","paper":"/paper/large-language-models-can-self-improve","paper_url":"https://arxiv.org/abs/2210.11610v2","paper_title":"Large Language Models Can Self-Improve","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":147,"model":"LLaMA 13B-maj1@k","metrics":{"Accuracy":"29.3","Parameters (Billion)":"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":148,"model":"Minerva 8B-maj1@k (8-shot)","metrics":{"Accuracy":" 28.4","Parameters (Billion)":"8"},"uses_additional_data":true,"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":149,"model":"GPT-2-Medium 355M + question-solution classifier (BS=5)","metrics":{"Accuracy":"20.8","Parameters (Billion)":"0.355"},"uses_additional_data":false,"paper_date":"2022-10-20","paper":"/paper/composing-ensembles-of-pre-trained-models-via","paper_url":"https://arxiv.org/abs/2210.11522v1","paper_title":"Composing Ensembles of Pre-trained Models via Iterative Consensus","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":150,"model":"GPT-Neo-2.7B + Self-Sampling","metrics":{"Accuracy":"19.5","Parameters (Billion)":"2.7"},"uses_additional_data":false,"paper_date":"2022-05-28","paper":"/paper/learning-from-self-sampled-correct-and","paper_url":"https://arxiv.org/abs/2205.14318v2","paper_title":"Learning Math Reasoning from Self-Sampled Correct and Partially-Correct Solutions","code":"https://github.com/microsoft/tracecodegen","n_code_links":1,"official":{"repos":["microsoft/tracecodegen"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_samples":11,"n_pointer_only_licence":0,"sample_list":"/paper/learning-from-self-sampled-correct-and#ran","syntology_url":"https://syntology.ai/paper/2205.14318","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14318"}}}},{"rank_in_archive_order":151,"model":"GPT-2-Medium 355M (fine-tuned, BS=5)","metrics":{"Accuracy":"18.3","Parameters (Billion)":"0.355"},"uses_additional_data":false,"paper_date":"2022-10-20","paper":"/paper/composing-ensembles-of-pre-trained-models-via","paper_url":"https://arxiv.org/abs/2210.11522v1","paper_title":"Composing Ensembles of Pre-trained Models via Iterative Consensus","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":152,"model":"LLaMA 7B (maj1@k)","metrics":{"Accuracy":"18.1","Parameters (Billion)":"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":153,"model":"PaLM 540B (few-shot)","metrics":{"Accuracy":"17.9","Parameters (Billion)":"540"},"uses_additional_data":true,"paper_date":"2022-05-24","paper":"/paper/large-language-models-are-zero-shot-reasoners","paper_url":"https://arxiv.org/abs/2205.11916v4","paper_title":"Large Language Models are Zero-Shot Reasoners","code":"https://github.com/kojima-takeshi188/zero_shot_cot","n_code_links":4,"official":{"repos":["kojima-takeshi188/zero_shot_cot"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":1,"sample_list":"/paper/large-language-models-are-zero-shot-reasoners#ran","syntology_url":"https://syntology.ai/paper/2205.11916","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.11916"}}}},{"rank_in_archive_order":154,"model":"PaLM 540B (Standard-Prompting)","metrics":{"Accuracy":"17.9","Parameters (Billion)":"540"},"uses_additional_data":false,"paper_date":"2022-10-20","paper":"/paper/large-language-models-can-self-improve","paper_url":"https://arxiv.org/abs/2210.11610v2","paper_title":"Large Language Models Can Self-Improve","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":155,"model":"LLaMA 13B","metrics":{"Accuracy":"17.8","Parameters (Billion)":"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":156,"model":"GPT-2-Medium 355M + question-solution classifier (BS=1)","metrics":{"Accuracy":"16.8","Parameters (Billion)":"0.355"},"uses_additional_data":false,"paper_date":"2022-10-20","paper":"/paper/composing-ensembles-of-pre-trained-models-via","paper_url":"https://arxiv.org/abs/2210.11522v1","paper_title":"Composing Ensembles of Pre-trained Models via Iterative Consensus","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":157,"model":"Minerva 8B (8-shot)","metrics":{"Accuracy":"16.2","Parameters (Billion)":"8"},"uses_additional_data":true,"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":158,"model":"GPT-2-Medium 355M (BS=5)","metrics":{"Accuracy":"12.2","Parameters (Billion)":"0.355"},"uses_additional_data":false,"paper_date":"2022-10-20","paper":"/paper/composing-ensembles-of-pre-trained-models-via","paper_url":"https://arxiv.org/abs/2210.11522v1","paper_title":"Composing Ensembles of Pre-trained Models via Iterative Consensus","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":159,"model":"LLaMA 7B","metrics":{"Accuracy":"11.0","Parameters (Billion)":"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":160,"model":"Text-davinci-002-175B (0-shot)","metrics":{"Accuracy":"10.4","Parameters (Billion)":"175"},"uses_additional_data":true,"paper_date":"2022-05-24","paper":"/paper/large-language-models-are-zero-shot-reasoners","paper_url":"https://arxiv.org/abs/2205.11916v4","paper_title":"Large Language Models are Zero-Shot Reasoners","code":"https://github.com/kojima-takeshi188/zero_shot_cot","n_code_links":4,"official":{"repos":["kojima-takeshi188/zero_shot_cot"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":1,"sample_list":"/paper/large-language-models-are-zero-shot-reasoners#ran","syntology_url":"https://syntology.ai/paper/2205.11916","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.11916"}}}},{"rank_in_archive_order":161,"model":"GPT-Neo 125M + Self-Sampling","metrics":{"Accuracy":"7.5","Parameters (Billion)":"0.125"},"uses_additional_data":false,"paper_date":"2022-05-28","paper":"/paper/learning-from-self-sampled-correct-and","paper_url":"https://arxiv.org/abs/2205.14318v2","paper_title":"Learning Math Reasoning from Self-Sampled Correct and Partially-Correct Solutions","code":"https://github.com/microsoft/tracecodegen","n_code_links":1,"official":{"repos":["microsoft/tracecodegen"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_samples":11,"n_pointer_only_licence":0,"sample_list":"/paper/learning-from-self-sampled-correct-and#ran","syntology_url":"https://syntology.ai/paper/2205.14318","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14318"}}}},{"rank_in_archive_order":162,"model":"UL2 20B (chain-of-thought)","metrics":{"Accuracy":"4.4","Parameters (Billion)":"20"},"uses_additional_data":false,"paper_date":"2022-05-10","paper":"/paper/unifying-language-learning-paradigms","paper_url":"https://arxiv.org/abs/2205.05131v3","paper_title":"UL2: Unifying Language Learning Paradigms","code":"https://github.com/google-research/google-research","n_code_links":2,"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":1,"n_samples":16,"n_pointer_only_licence":0,"sample_list":"/paper/unifying-language-learning-paradigms#ran","syntology_url":"https://syntology.ai/paper/2205.05131","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.05131"}}}},{"rank_in_archive_order":163,"model":"PaLM 8B (8-shot)","metrics":{"Accuracy":"4.1","Parameters (Billion)":"8"},"uses_additional_data":true,"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":164,"model":"UL2 20B (0-shot)","metrics":{"Accuracy":"4.1","Parameters (Billion)":"20"},"uses_additional_data":false,"paper_date":"2022-05-10","paper":"/paper/unifying-language-learning-paradigms","paper_url":"https://arxiv.org/abs/2205.05131v3","paper_title":"UL2: Unifying Language Learning Paradigms","code":"https://github.com/google-research/google-research","n_code_links":2,"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":1,"n_samples":16,"n_pointer_only_licence":0,"sample_list":"/paper/unifying-language-learning-paradigms#ran","syntology_url":"https://syntology.ai/paper/2205.05131","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.05131"}}}}],"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), 230 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 1,484 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and 168 proposed a result; of those 168, 127 gave no cell that passed the extractor's own checks, 41 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":164,"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":1484,"candidates":230,"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":168,"no_cell_passed_checks":127,"rejected_by_independent_check":41,"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; 168 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":168,"shown_on_page":100,"no_cell_split":{"no_cell_passed_checks_in_ledger":127,"rows_refused_by_rule":127,"rows_no_cell_passed_checks":0},"rows":[{"arxiv_id":"2609.30054","outcome":"rejected","reason":null},{"arxiv_id":"2609.21675","outcome":"rejected","reason":null},{"arxiv_id":"2609.19606","outcome":"refused_by_rule","reason":"the value is not on the scale of the leaderboard column's archive values"},{"arxiv_id":"2609.16372","outcome":"refused_by_rule","reason":"the model gave no value to check against the cell"},{"arxiv_id":"2609.13356","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2609.12243","outcome":"rejected","reason":null},{"arxiv_id":"2609.02264","outcome":"refused_by_rule","reason":"the number the model quoted is not the number printed in the cell it pointed at"},{"arxiv_id":"2608.30908","outcome":"refused_by_rule","reason":"the number the model quoted is not the number printed in the cell it pointed at"},{"arxiv_id":"2608.26550","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2608.24469","outcome":"rejected","reason":null},{"arxiv_id":"2608.09542","outcome":"rejected","reason":null},{"arxiv_id":"2607.28166","outcome":"rejected","reason":null},{"arxiv_id":"2607.18532","outcome":"refused_by_rule","reason":"the model pointed at a header row; the model gave no value to check against the cell"},{"arxiv_id":"2607.16252","outcome":"rejected","reason":null},{"arxiv_id":"2606.31779","outcome":"rejected","reason":null},{"arxiv_id":"2606.31413","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2606.26120","outcome":"refused_by_rule","reason":"the row is an ablation variant, not the method itself"},{"arxiv_id":"2606.20621","outcome":"refused_by_rule","reason":"the value is not on the scale of the leaderboard column's archive values"},{"arxiv_id":"2606.13867","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2606.11854","outcome":"refused_by_rule","reason":"the model gave no value to check against the cell"},{"arxiv_id":"2606.09886","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"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":"2606.08411","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2606.05859","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric; one configuration gave two values for one column"},{"arxiv_id":"2606.04964","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2606.02559","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2606.02359","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":"2606.02241","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2606.00494","outcome":"refused_by_rule","reason":"the row label the model quoted is not the row's label"},{"arxiv_id":"2605.31164","outcome":"refused_by_rule","reason":"the row label the model quoted is not the row's label"},{"arxiv_id":"2605.29716","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2605.29656","outcome":"rejected","reason":null},{"arxiv_id":"2605.29398","outcome":"refused_by_rule","reason":"the row is an ablation variant, not the method itself"},{"arxiv_id":"2605.27081","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2605.26733","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric; one configuration gave two values for one column"},{"arxiv_id":"2605.25745","outcome":"refused_by_rule","reason":"the table does not name the leaderboard's dataset; the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2605.25198","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2605.24564","outcome":"refused_by_rule","reason":"the model gave no value to check against the cell"},{"arxiv_id":"2605.23200","outcome":"refused_by_rule","reason":"the row label the model quoted is not the row's label"},{"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":"2605.21318","outcome":"refused_by_rule","reason":"the number the model quoted is not the number printed in the cell it pointed at"},{"arxiv_id":"2605.20722","outcome":"rejected","reason":null},{"arxiv_id":"2605.20075","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2605.17104","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2605.17003","outcome":"refused_by_rule","reason":"the value is not on the scale of the leaderboard column's archive values; the number the model quoted is not the number printed in the cell it pointed at"},{"arxiv_id":"2605.16941","outcome":"rejected","reason":null},{"arxiv_id":"2605.16865","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":"2605.13295","outcome":"refused_by_rule","reason":"the number the model quoted is not the number printed in the cell it pointed at"},{"arxiv_id":"2605.12825","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2605.11974","outcome":"refused_by_rule","reason":"the table does not name the leaderboard's dataset"},{"arxiv_id":"2605.11726","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":"2605.11712","outcome":"rejected","reason":null},{"arxiv_id":"2605.11125","outcome":"rejected","reason":null},{"arxiv_id":"2605.10195","outcome":"refused_by_rule","reason":"the number the model quoted is not the number printed in the cell it pointed at"},{"arxiv_id":"2605.09922","outcome":"refused_by_rule","reason":"the row is an ablation variant, not the method itself"},{"arxiv_id":"2605.09907","outcome":"refused_by_rule","reason":"the number the model quoted is not the number printed in the cell it pointed at"},{"arxiv_id":"2605.09536","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2605.09346","outcome":"rejected","reason":null},{"arxiv_id":"2605.09188","outcome":"refused_by_rule","reason":"the number the model quoted is not the number printed in the cell it pointed at"},{"arxiv_id":"2605.08134","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":"2605.05995","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2605.03862","outcome":"rejected","reason":null},{"arxiv_id":"2605.02263","outcome":"refused_by_rule","reason":"the row is an ablation variant, not the method itself"},{"arxiv_id":"2605.01910","outcome":"refused_by_rule","reason":"the number the model quoted is not the number printed in the cell it pointed at"},{"arxiv_id":"2605.00195","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2604.25039","outcome":"rejected","reason":null},{"arxiv_id":"2604.24357","outcome":"refused_by_rule","reason":"the table does not name the leaderboard's dataset"},{"arxiv_id":"2604.18995","outcome":"refused_by_rule","reason":"the row label the model quoted is not the row's label"},{"arxiv_id":"2604.15750","outcome":"rejected","reason":null},{"arxiv_id":"2604.15672","outcome":"rejected","reason":null},{"arxiv_id":"2604.14853","outcome":"refused_by_rule","reason":"the model gave no value to check against the cell"},{"arxiv_id":"2604.14602","outcome":"refused_by_rule","reason":"the value is not on the scale of the leaderboard column's archive values; the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2604.14246","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2604.13846","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2604.13552","outcome":"rejected","reason":null},{"arxiv_id":"2604.12928","outcome":"refused_by_rule","reason":"the number the model quoted is not the number printed in the cell it pointed at; the row label the model quoted is not the row's label"},{"arxiv_id":"2604.12374","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2604.09791","outcome":"refused_by_rule","reason":"the row label the model quoted is not the row's label"},{"arxiv_id":"2604.08302","outcome":"rejected","reason":null},{"arxiv_id":"2604.01622","outcome":"rejected","reason":null},{"arxiv_id":"2604.00012","outcome":"rejected","reason":null},{"arxiv_id":"2603.26511","outcome":"refused_by_rule","reason":"the model gave no value to check against the cell; the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2603.25702","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2603.22352","outcome":"refused_by_rule","reason":"the row is an ablation variant, not the method itself"},{"arxiv_id":"2603.22300","outcome":"refused_by_rule","reason":"the table does not name the leaderboard's dataset; the number the model quoted is not the number printed in the cell it pointed at"},{"arxiv_id":"2603.22016","outcome":"refused_by_rule","reason":"the row label the model quoted is not the row's label"},{"arxiv_id":"2603.20640","outcome":"refused_by_rule","reason":"the model gave no value to check against the cell"},{"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":"2603.16331","outcome":"rejected","reason":null},{"arxiv_id":"2603.13792","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2603.10243","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2603.10088","outcome":"rejected","reason":null},{"arxiv_id":"2603.08185","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2603.08026","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2603.06859","outcome":"refused_by_rule","reason":"the row is an ablation variant, not the method itself"},{"arxiv_id":"2603.04678","outcome":"refused_by_rule","reason":"the row is an ablation variant, not the method itself"},{"arxiv_id":"2603.02630","outcome":"rejected","reason":null},{"arxiv_id":"2603.00573","outcome":"refused_by_rule","reason":"the number the model quoted is not the number printed in the cell it pointed at"},{"arxiv_id":"2602.23349","outcome":"refused_by_rule","reason":"the model pointed at a header row"},{"arxiv_id":"2602.23225","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2602.22538","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2602.22296","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric; the model gave no value to check against the cell"},{"arxiv_id":"2602.15143","outcome":"rejected","reason":null},{"arxiv_id":"2602.14451","outcome":"rejected","reason":null},{"arxiv_id":"2602.13773","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2602.12262","outcome":"refused_by_rule","reason":"the row label the model quoted is not the row's label"},{"arxiv_id":"2602.12113","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2602.10623","outcome":"refused_by_rule","reason":"the row label the model quoted is not the row's label"},{"arxiv_id":"2602.08404","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2602.06953","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"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":"2602.05992","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2602.05536","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2602.03120","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2602.02103","outcome":"rejected","reason":null},{"arxiv_id":"2602.02099","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2602.01982","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2602.01698","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":"2601.22527","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2601.21484","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2601.21358","outcome":"refused_by_rule","reason":"the model pointed at a header row"},{"arxiv_id":"2601.20326","outcome":"refused_by_rule","reason":"the model pointed at a header row; the number the model quoted is not the number printed in the cell it pointed at"},{"arxiv_id":"2601.18533","outcome":"refused_by_rule","reason":"the row label the model quoted is not the row's label"},{"arxiv_id":"2601.17917","outcome":"refused_by_rule","reason":"the row label the model quoted is not the row's label"},{"arxiv_id":"2601.15708","outcome":"rejected","reason":null},{"arxiv_id":"2601.15498","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2601.07568","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":"2601.07155","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2601.06022","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2601.05167","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2601.02569","outcome":"refused_by_rule","reason":"the row label the model quoted is not the row's label"},{"arxiv_id":"2601.02236","outcome":"rejected","reason":null},{"arxiv_id":"2512.23461","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2512.14681","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2512.14395","outcome":"refused_by_rule","reason":"the row label the model quoted is not the row's label"},{"arxiv_id":"2512.11391","outcome":"refused_by_rule","reason":"the row is an ablation variant, not the method itself"},{"arxiv_id":"2512.10978","outcome":"rejected","reason":null},{"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":"2511.08043","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2511.05664","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2511.04805","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2511.00351","outcome":"refused_by_rule","reason":"the model gave no value to check against the cell"},{"arxiv_id":"2511.00056","outcome":"refused_by_rule","reason":"the row label the model quoted is not the row's label"},{"arxiv_id":"2510.27355","outcome":"rejected","reason":null},{"arxiv_id":"2510.22437","outcome":"rejected","reason":null},{"arxiv_id":"2510.21473","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2510.07364","outcome":"rejected","reason":null},{"arxiv_id":"2510.07312","outcome":"rejected","reason":null},{"arxiv_id":"2510.05069","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2510.04474","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":"2510.00685","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"},{"arxiv_id":"2509.24248","outcome":"rejected","reason":null},{"arxiv_id":"2509.24245","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2509.16598","outcome":"rejected","reason":null},{"arxiv_id":"2509.14651","outcome":"refused_by_rule","reason":"the row label the model quoted is not the row's label; the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2508.19564","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2508.18847","outcome":"refused_by_rule","reason":"the value is not on the scale of the leaderboard column's archive values"},{"arxiv_id":"2508.18672","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2508.15868","outcome":"rejected","reason":null},{"arxiv_id":"2508.13037","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric; one configuration gave two values for one column"}]},"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":77,"rows_with_any_sample_ran":76,"rows_with_a_run_with_no_instrument_failure":67,"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":67,"rows_whose_official_repository_has_a_sample_that_ran":47,"rows_whose_official_repository_has_a_run_with_no_instrument_failure":38,"rows_community_repositories_only":4,"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":28,"distinct_papers_with_any_sample_ran":27,"distinct_papers_with_a_run_with_no_instrument_failure":25,"samples_over_distinct_papers":{"n_ran":277,"n_constructed":18,"n_ran_checked":163,"n_instrument":114,"n_unverified":93,"n_samples":370,"n_pointer_only_licence":115,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":868,"n_constructed":81,"n_ran_checked":480,"n_instrument":388,"n_unverified":325,"n_samples":1193,"n_pointer_only_licence":287,"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":"2c77dfbe8f7fcb63c284c8afbd390ed45b042dd5445869c5ee3990679637646e","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}