{"url":"/task/math-word-problem-solving","name":"Math Word Problem Solving","slug":"math-word-problem-solving","description_markdown":"A math word problem is a mathematical exercise (such as in a textbook, worksheet, or exam) where significant background information on the problem is presented in ordinary language rather than in mathematical notation. As most word problems involve a narrative of some sort, they are sometimes referred to as story problems and may vary in the amount of technical language used.","categories":[{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":107,"papers_with_code":80,"benchmarks":13,"benchmark_tables_in_archive":13,"benchmark_tables_shown":13,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":23,"subtasks":0,"parent_tasks":2},"benchmarks":[{"leaderboard":"/sota/math-word-problem-solving-on-math","slug":"math-word-problem-solving-on-math","dataset":"MATH","dataset_url":"/dataset/math","rows_in_archive":135,"metrics":["Accuracy","Parameters (Billions)"],"first_row_in_archive_order":{"model":"Gemini 2.0 Flash Experimental","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/math-word-problem-solving-on-svamp","slug":"math-word-problem-solving-on-svamp","dataset":"SVAMP","dataset_url":"/dataset/svamp","rows_in_archive":26,"metrics":["Execution Accuracy","Accuracy"],"first_row_in_archive_order":{"model":"GPT-4 (Teaching-Inspired)","paper_title":"Teaching-Inspired Integrated Prompting Framework: A Novel Approach for Enhancing Reasoning in Large Language Models","paper_url":"/paper/teaching-inspired-integrated-prompting","paper_date":"2024-10-10","arxiv_id":"2410.08068","code_links":[{"title":"sallytan13/teaching-inspired-prompting","url":"https://github.com/sallytan13/teaching-inspired-prompting"}],"syntology":{"n":8,"n_ran":8,"n_unverified":0,"n_pointer_only":8}}},{"leaderboard":"/sota/math-word-problem-solving-on-mawps","slug":"math-word-problem-solving-on-mawps","dataset":"MAWPS","dataset_url":"/dataset/mawps","rows_in_archive":25,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"OpenMath-CodeLlama-70B (w/ code)","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_url":"/paper/openmathinstruct-1-a-1-8-million-math","paper_date":"2024-02-15","arxiv_id":"2402.10176","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"syntology":null}},{"leaderboard":"/sota/math-word-problem-solving-on-math23k","slug":"math-word-problem-solving-on-math23k","dataset":"Math23K","dataset_url":"/dataset/math23k","rows_in_archive":19,"metrics":["Accuracy (5-fold)","Accuracy (training-test)","weakly-supervised"],"first_row_in_archive_order":{"model":"GPT-4 (Teaching-Inspired)","paper_title":"Teaching-Inspired Integrated Prompting Framework: A Novel Approach for Enhancing Reasoning in Large Language Models","paper_url":"/paper/teaching-inspired-integrated-prompting","paper_date":"2024-10-10","arxiv_id":"2410.08068","code_links":[{"title":"sallytan13/teaching-inspired-prompting","url":"https://github.com/sallytan13/teaching-inspired-prompting"}],"syntology":{"n":8,"n_ran":8,"n_unverified":0,"n_pointer_only":8}}},{"leaderboard":"/sota/math-word-problem-solving-on-alg514","slug":"math-word-problem-solving-on-alg514","dataset":"ALG514","dataset_url":"/dataset/alg514","rows_in_archive":10,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"MixedSP","paper_title":"Learning from Explicit and Implicit Supervision Jointly For Algebra Word Problems","paper_url":"/paper/learning-from-explicit-and-implicit","paper_date":"2016-11-01","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/math-word-problem-solving-on-asdiv-a","slug":"math-word-problem-solving-on-asdiv-a","dataset":"ASDiv-A","dataset_url":"/dataset/asdiv","rows_in_archive":9,"metrics":["Execution Accuracy"],"first_row_in_archive_order":{"model":"ATHENA (roberta-large)","paper_title":"ATHENA: Mathematical Reasoning with Thought Expansion","paper_url":"/paper/athena-mathematical-reasoning-with-thought","paper_date":"2023-11-02","arxiv_id":"2311.01036","code_links":[{"title":"the-jb/athena-math","url":"https://github.com/the-jb/athena-math"}],"syntology":null}},{"leaderboard":"/sota/math-word-problem-solving-on-paramawps","slug":"math-word-problem-solving-on-paramawps","dataset":"ParaMAWPS","dataset_url":"/dataset/paramawps","rows_in_archive":6,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"DeBERTa (VM)","paper_title":"Math Word Problem Solving by Generating Linguistic Variants of Problem Statements","paper_url":"/paper/math-word-problem-solving-by-generating","paper_date":"2023-06-24","arxiv_id":"2306.13899","code_links":[{"title":"starscream-11813/variational-mathematical-reasoning","url":"https://github.com/starscream-11813/variational-mathematical-reasoning"}],"syntology":null}},{"leaderboard":"/sota/math-word-problem-solving-on-draw-1k","slug":"math-word-problem-solving-on-draw-1k","dataset":"DRAW-1K","dataset_url":"/dataset/draw-1k","rows_in_archive":5,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"EPT","paper_title":"EPT-X: An Expression-Pointer Transformer model that generates eXplanations for numbers","paper_url":"/paper/ept-x-an-expression-pointer-transformer-model","paper_date":"","arxiv_id":null,"code_links":[{"title":"snucclab/ept-x","url":"https://github.com/snucclab/ept-x"}],"syntology":null}},{"leaderboard":"/sota/math-word-problem-solving-on-mathqa","slug":"math-word-problem-solving-on-mathqa","dataset":"MathQA","dataset_url":"/dataset/mathqa","rows_in_archive":5,"metrics":["Answer Accuracy"],"first_row_in_archive_order":{"model":"ELASTIC (RoBERTa-large)","paper_title":"ELASTIC: Numerical Reasoning with Adaptive Symbolic Compiler","paper_url":"/paper/elastic-numerical-reasoning-with-adaptive","paper_date":"2022-10-18","arxiv_id":"2210.10105","code_links":[{"title":"neurasearch/neurips-2022-submission-3358","url":"https://github.com/neurasearch/neurips-2022-submission-3358"}],"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/math-word-problem-solving-on-svamp-1-n","slug":"math-word-problem-solving-on-svamp-1-n","dataset":"SVAMP (1:N)","dataset_url":"/dataset/svamp","rows_in_archive":2,"metrics":["Execution Accuracy"],"first_row_in_archive_order":{"model":"ATHENA (roberta-large)","paper_title":"ATHENA: Mathematical Reasoning with Thought Expansion","paper_url":"/paper/athena-mathematical-reasoning-with-thought","paper_date":"2023-11-02","arxiv_id":"2311.01036","code_links":[{"title":"the-jb/athena-math","url":"https://github.com/the-jb/athena-math"}],"syntology":null}},{"leaderboard":"/sota/math-word-problem-solving-on-gsm-plus","slug":"math-word-problem-solving-on-gsm-plus","dataset":"GSM-Plus","dataset_url":"/dataset/gsm-plus","rows_in_archive":1,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"GPT-4","paper_title":"GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers","paper_url":"/paper/gsm-plus-a-comprehensive-benchmark-for","paper_date":"2024-02-29","arxiv_id":"2402.19255","code_links":[{"title":"qtli/gsm-plus","url":"https://github.com/qtli/gsm-plus"}],"syntology":null}},{"leaderboard":"/sota/math-word-problem-solving-on-math-minival","slug":"math-word-problem-solving-on-math-minival","dataset":"MATH minival","dataset_url":"/dataset/math","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Process Supervision (GPT-4)","paper_title":"Let's Verify Step by Step","paper_url":"/paper/let-s-verify-step-by-step-1","paper_date":"2023-05-31","arxiv_id":"2305.20050","code_links":[{"title":"openai/prm800k","url":"https://github.com/openai/prm800k"},{"title":"gentopia-ai/gentopia","url":"https://github.com/gentopia-ai/gentopia"},{"title":"consequentai/fneval","url":"https://github.com/consequentai/fneval"}],"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/math-word-problem-solving-on-pen","slug":"math-word-problem-solving-on-pen","dataset":"PEN","dataset_url":"/dataset/pen","rows_in_archive":1,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"EPT-X","paper_title":"EPT-X: An Expression-Pointer Transformer model that generates eXplanations for numbers","paper_url":"/paper/ept-x-an-expression-pointer-transformer-model","paper_date":"","arxiv_id":null,"code_links":[{"title":"snucclab/ept-x","url":"https://github.com/snucclab/ept-x"}],"syntology":null}}],"datasets":[{"url":"/dataset/math","name":"MATH","full_name":"","num_papers_in_archive":1330},{"url":"/dataset/svamp","name":"SVAMP","full_name":"Simple Variations on Arithmetic Math word Problems","num_papers_in_archive":362},{"url":"/dataset/mathvista","name":"MathVista","full_name":"Mathematical Reasoning of in Visual Contexts","num_papers_in_archive":242},{"url":"/dataset/mathqa","name":"MathQA","full_name":"","num_papers_in_archive":159},{"url":"/dataset/asdiv","name":"ASDiv","full_name":"Academia Sinica Diverse MWP Dataset","num_papers_in_archive":150},{"url":"/dataset/mawps","name":"MAWPS","full_name":"MAth Word ProblemS","num_papers_in_archive":122},{"url":"/dataset/mgsm","name":"MGSM","full_name":"Multilingual Grade School Math","num_papers_in_archive":107},{"url":"/dataset/math23k","name":"Math23K","full_name":"Math23K for Math Word Problem Solving","num_papers_in_archive":95},{"url":"/dataset/geometry3k","name":"Geometry3K","full_name":"","num_papers_in_archive":45},{"url":"/dataset/iconqa","name":"IconQA","full_name":"Icon Question Answering","num_papers_in_archive":42},{"url":"/dataset/geos","name":"GeoS","full_name":"","num_papers_in_archive":24},{"url":"/dataset/alg514","name":"ALG514","full_name":"","num_papers_in_archive":22},{"url":"/dataset/gsm-plus","name":"GSM-Plus","full_name":"","num_papers_in_archive":17},{"url":"/dataset/pgps9k","name":"PGPS9K","full_name":"","num_papers_in_archive":14},{"url":"/dataset/pen","name":"PEN","full_name":"Problems with Explanations for Numbers","num_papers_in_archive":5},{"url":"/dataset/draw-1k","name":"DRAW-1K","full_name":"Diverse Algebra Word Problem Set","num_papers_in_archive":4},{"url":"/dataset/dart-math-hard","name":"DART-Math-Hard","full_name":"","num_papers_in_archive":2},{"url":"/dataset/paramawps","name":"ParaMAWPS","full_name":"Paraphrased Math Word Problem Solving Repository","num_papers_in_archive":2},{"url":"/dataset/dart-math-uniform","name":"DART-Math-Uniform","full_name":"","num_papers_in_archive":1},{"url":"/dataset/synthetic-grade-school-math-sgsm","name":"Educational Grade School Math (EGSM)","full_name":"","num_papers_in_archive":1},{"url":"/dataset/mathmc","name":"MathMC","full_name":"","num_papers_in_archive":1},{"url":"/dataset/mathtof","name":"MathToF","full_name":"","num_papers_in_archive":1},{"url":"/dataset/mmos","name":"MMOS","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/mathematical-question-answering","name":"Mathematical Question Answering"},{"url":"/task/mathematical-reasoning","name":"Mathematical Reasoning"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":80,"tagged_in_all":107,"items":[{"url":"/paper/llama-open-and-efficient-foundation-language-1","title":"LLaMA: Open and Efficient Foundation Language Models","date":"2023-02-27","arxiv_id":"2302.13971","repositories_listed":57,"syntology":{"n":58,"n_ran":26,"n_unverified":32,"n_pointer_only":4}},{"url":"/paper/llama-2-open-foundation-and-fine-tuned-chat","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","date":"2023-07-18","arxiv_id":"2307.09288","repositories_listed":19,"syntology":{"n":52,"n_ran":31,"n_unverified":21,"n_pointer_only":16}},{"url":"/paper/deberta-decoding-enhanced-bert-with","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","date":"2020-06-05","arxiv_id":"2006.03654","repositories_listed":14,"syntology":{"n":13,"n_ran":4,"n_unverified":9,"n_pointer_only":3}},{"url":"/paper/analysing-mathematical-reasoning-abilities-of-1","title":"Analysing Mathematical Reasoning Abilities of Neural Models","date":"2019-04-02","arxiv_id":"1904.01557","repositories_listed":7,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/qwen2-technical-report","title":"Qwen2 Technical Report","date":"2024-07-15","arxiv_id":"2407.10671","repositories_listed":6,"syntology":null},{"url":"/paper/mixtral-of-experts","title":"Mixtral of Experts","date":"2024-01-08","arxiv_id":"2401.04088","repositories_listed":6,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/mistral-7b","title":"Mistral 7B","date":"2023-10-10","arxiv_id":"2310.06825","repositories_listed":6,"syntology":{"n":11,"n_ran":9,"n_unverified":2,"n_pointer_only":1}},{"url":"/paper/deepseekmath-pushing-the-limits-of","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","date":"2024-02-05","arxiv_id":"2402.03300","repositories_listed":5,"syntology":{"n":24,"n_ran":8,"n_unverified":16,"n_pointer_only":0}},{"url":"/paper/measuring-mathematical-problem-solving-with","title":"Measuring Mathematical Problem Solving With the MATH Dataset","date":"2021-03-05","arxiv_id":"2103.03874","repositories_listed":5,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/large-language-models-are-zero-shot-reasoners","title":"Large Language Models are Zero-Shot Reasoners","date":"2022-05-24","arxiv_id":"2205.11916","repositories_listed":4,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":1}},{"url":"/paper/math-shepherd-a-label-free-step-by-step","title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations","date":"2023-12-14","arxiv_id":"2312.08935","repositories_listed":3,"syntology":null},{"url":"/paper/let-s-verify-step-by-step-1","title":"Let's Verify Step by Step","date":"2023-05-31","arxiv_id":"2305.20050","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/sparks-of-artificial-general-intelligence","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","date":"2023-03-22","arxiv_id":"2303.12712","repositories_listed":3,"syntology":{"n":10,"n_ran":0,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/pal-program-aided-language-models","title":"PAL: Program-aided Language Models","date":"2022-11-18","arxiv_id":"2211.10435","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/are-nlp-models-really-able-to-solve-simple","title":"Are NLP Models really able to Solve Simple Math Word Problems?","date":"2021-03-12","arxiv_id":"2103.07191","repositories_listed":3,"syntology":null},{"url":"/paper/parameter-efficient-sparsity-crafting-from","title":"Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks","date":"2024-01-05","arxiv_id":"2401.02731","repositories_listed":2,"syntology":null},{"url":"/paper/an-empirical-study-on-challenging-math","title":"MathChat: Converse to Tackle Challenging Math Problems with LLM Agents","date":"2023-06-02","arxiv_id":"2306.01337","repositories_listed":2,"syntology":null},{"url":"/paper/reticl-sequential-retrieval-of-in-context","title":"RetICL: Sequential Retrieval of In-Context Examples with Reinforcement Learning","date":"2023-05-23","arxiv_id":"2305.14502","repositories_listed":2,"syntology":null},{"url":"/paper/logicsolver-towards-interpretable-math-word","title":"LogicSolver: Towards Interpretable Math Word Problem Solving with Logical Prompt-enhanced Learning","date":"2022-05-17","arxiv_id":"2205.08232","repositories_listed":2,"syntology":null},{"url":"/paper/a-diversity-enhanced-knowledge-distillation","title":"A Diversity-Enhanced Knowledge Distillation Model for Practical Math Word Problem Solving","date":"2025-01-07","arxiv_id":"2501.03670","repositories_listed":1,"syntology":null},{"url":"/paper/sbi-rag-enhancing-math-word-problem-solving","title":"SBI-RAG: Enhancing Math Word Problem Solving for Students through Schema-Based Instruction and Retrieval-Augmented Generation","date":"2024-10-17","arxiv_id":"2410.13293","repositories_listed":1,"syntology":null},{"url":"/paper/teaching-inspired-integrated-prompting","title":"Teaching-Inspired Integrated Prompting Framework: A Novel Approach for Enhancing Reasoning in Large Language Models","date":"2024-10-10","arxiv_id":"2410.08068","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_unverified":0,"n_pointer_only":8}},{"url":"/paper/openmathinstruct-2-accelerating-ai-for-math","title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","date":"2024-10-02","arxiv_id":"2410.01560","repositories_listed":1,"syntology":{"n":15,"n_ran":0,"n_unverified":15,"n_pointer_only":0}},{"url":"/paper/step-dpo-step-wise-preference-optimization","title":"Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs","date":"2024-06-26","arxiv_id":"2406.18629","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_unverified":5,"n_pointer_only":12}},{"url":"/paper/dart-math-difficulty-aware-rejection-tuning-1","title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","date":"2024-06-18","arxiv_id":"2407.13690","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/alphamath-almost-zero-process-supervision","title":"AlphaMath Almost Zero: Process Supervision without Process","date":"2024-05-06","arxiv_id":"2405.03553","repositories_listed":1,"syntology":null},{"url":"/paper/achieving-97-on-gsm8k-deeply-understanding","title":"Achieving >97% on GSM8K: Deeply Understanding the Problems Makes LLMs Better Solvers for Math Word Problems","date":"2024-04-23","arxiv_id":"2404.14963","repositories_listed":1,"syntology":null},{"url":"/paper/toward-self-improvement-of-llms-via","title":"Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing","date":"2024-04-18","arxiv_id":"2404.12253","repositories_listed":1,"syntology":{"n":18,"n_ran":13,"n_unverified":5,"n_pointer_only":18}},{"url":"/paper/macm-utilizing-a-multi-agent-system-for","title":"MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems","date":"2024-04-06","arxiv_id":"2404.04735","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/branch-train-mix-mixing-expert-llms-into-a","title":"Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM","date":"2024-03-12","arxiv_id":"2403.07816","repositories_listed":1,"syntology":null}],"syntology_records":18,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}