{"url":"/task/math","name":"Math","slug":"math","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":1596,"papers_with_code":765,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":6,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/gsm-plus","name":"GSM-Plus","full_name":"","num_papers_in_archive":17},{"url":"/dataset/mathbench","name":"MathBench","full_name":"MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmark","num_papers_in_archive":16},{"url":"/dataset/dart-math-hard","name":"DART-Math-Hard","full_name":"","num_papers_in_archive":2},{"url":"/dataset/dart-math-uniform","name":"DART-Math-Uniform","full_name":"","num_papers_in_archive":1},{"url":"/dataset/mm-eval","name":"MM-Eval","full_name":"Modern Mongolian Evaluation","num_papers_in_archive":1},{"url":"/dataset/valimath","name":"ValiMath","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"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":765,"tagged_in_all":1596,"items":[{"url":"/paper/chain-of-thought-prompting-elicits-reasoning","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","date":"2022-01-28","arxiv_id":"2201.11903","repositories_listed":19,"syntology":{"n":7,"n_ran":2,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/awq-activation-aware-weight-quantization-for","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","date":"2023-06-01","arxiv_id":"2306.00978","repositories_listed":12,"syntology":{"n":18,"n_ran":12,"n_unverified":6,"n_pointer_only":2}},{"url":"/paper/gpt-4-technical-report-1","title":"GPT-4 Technical Report","date":"2023-03-15","arxiv_id":"2303.08774","repositories_listed":11,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":1}},{"url":"/paper/translating-mathematical-formula-images-to","title":"Translating Math Formula Images to LaTeX Sequences Using Deep Neural Networks with Sequence-level Training","date":"2019-08-29","arxiv_id":"1908.11415","repositories_listed":8,"syntology":null},{"url":"/paper/chatglm-a-family-of-large-language-models","title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","date":"2024-06-18","arxiv_id":"2406.12793","repositories_listed":7,"syntology":{"n":29,"n_ran":15,"n_unverified":14,"n_pointer_only":0}},{"url":"/paper/palm-scaling-language-modeling-with-pathways-1","title":"PaLM: Scaling Language Modeling with Pathways","date":"2022-04-05","arxiv_id":"2204.02311","repositories_listed":7,"syntology":{"n":37,"n_ran":30,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/qwen2-5-technical-report","title":"Qwen2.5 Technical Report","date":"2024-12-19","arxiv_id":"2412.15115","repositories_listed":6,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"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/beyond-the-imitation-game-quantifying-and","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","date":"2022-06-09","arxiv_id":"2206.04615","repositories_listed":6,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/training-verifiers-to-solve-math-word","title":"Training Verifiers to Solve Math Word Problems","date":"2021-10-27","arxiv_id":"2110.14168","repositories_listed":6,"syntology":{"n":7,"n_ran":1,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/process-reinforcement-through-implicit","title":"Process Reinforcement through Implicit Rewards","date":"2025-02-03","arxiv_id":"2502.01456","repositories_listed":5,"syntology":{"n":17,"n_ran":2,"n_unverified":15,"n_pointer_only":0}},{"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/full-page-handwriting-recognition-via-image","title":"Full Page Handwriting Recognition via Image to Sequence Extraction","date":"2021-03-11","arxiv_id":"2103.06450","repositories_listed":5,"syntology":null},{"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/the-matrix-calculus-you-need-for-deep","title":"The Matrix Calculus You Need For Deep Learning","date":"2018-02-05","arxiv_id":"1802.01528","repositories_listed":5,"syntology":null},{"url":"/paper/mamut-a-novel-framework-for-modifying","title":"MAMUT: A Novel Framework for Modifying Mathematical Formulas for the Generation of Specialized Datasets for Language Model Training","date":"2025-02-28","arxiv_id":"2502.20855","repositories_listed":4,"syntology":null},{"url":"/paper/logic-rl-unleashing-llm-reasoning-with-rule","title":"Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning","date":"2025-02-20","arxiv_id":"2502.14768","repositories_listed":4,"syntology":{"n":23,"n_ran":10,"n_unverified":13,"n_pointer_only":0}},{"url":"/paper/on-the-emergence-of-thinking-in-llms-i","title":"On the Emergence of Thinking in LLMs I: Searching for the Right Intuition","date":"2025-02-10","arxiv_id":"2502.06773","repositories_listed":4,"syntology":{"n":13,"n_ran":0,"n_unverified":13,"n_pointer_only":0}},{"url":"/paper/mario-eval-evaluate-your-math-llm-with-your","title":"MARIO Eval: Evaluate Your Math LLM with your Math LLM--A mathematical dataset evaluation toolkit","date":"2024-04-22","arxiv_id":"2404.13925","repositories_listed":4,"syntology":{"n":13,"n_ran":8,"n_unverified":5,"n_pointer_only":13}},{"url":"/paper/starcoder-2-and-the-stack-v2-the-next","title":"StarCoder 2 and The Stack v2: The Next Generation","date":"2024-02-29","arxiv_id":"2402.19173","repositories_listed":4,"syntology":null},{"url":"/paper/llemma-an-open-language-model-for-mathematics","title":"Llemma: An Open Language Model For Mathematics","date":"2023-10-16","arxiv_id":"2310.10631","repositories_listed":4,"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/how-is-chatgpt-s-behavior-changing-over-time","title":"How is ChatGPT's behavior changing over time?","date":"2023-07-18","arxiv_id":"2307.09009","repositories_listed":4,"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":5}},{"url":"/paper/language-models-are-multilingual-chain-of","title":"Language Models are Multilingual Chain-of-Thought Reasoners","date":"2022-10-06","arxiv_id":"2210.03057","repositories_listed":4,"syntology":null},{"url":"/paper/memorizing-transformers-1","title":"Memorizing Transformers","date":"2022-03-16","arxiv_id":"2203.08913","repositories_listed":4,"syntology":{"n":34,"n_ran":20,"n_unverified":14,"n_pointer_only":2}},{"url":"/paper/ttrl-test-time-reinforcement-learning","title":"TTRL: Test-Time Reinforcement Learning","date":"2025-04-22","arxiv_id":"2504.16084","repositories_listed":3,"syntology":{"n":16,"n_ran":7,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/xlstm-7b-a-recurrent-llm-for-fast-and","title":"xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference","date":"2025-03-17","arxiv_id":"2503.13427","repositories_listed":3,"syntology":{"n":5,"n_ran":1,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/reasonflux-hierarchical-llm-reasoning-via","title":"ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates","date":"2025-02-10","arxiv_id":"2502.06772","repositories_listed":3,"syntology":null},{"url":"/paper/limo-less-is-more-for-reasoning","title":"LIMO: Less is More for Reasoning","date":"2025-02-05","arxiv_id":"2502.03387","repositories_listed":3,"syntology":null},{"url":"/paper/kimi-k1-5-scaling-reinforcement-learning-with","title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","date":"2025-01-22","arxiv_id":"2501.12599","repositories_listed":3,"syntology":{"n":10,"n_ran":3,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/rstar-math-small-llms-can-master-math","title":"rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking","date":"2025-01-08","arxiv_id":"2501.04519","repositories_listed":3,"syntology":null}],"syntology_records":21,"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"}}