{"task":"Math Word Problem Solving","dataset":"ASDiv-A","metric_names":["Execution Accuracy"],"rows":[{"id":25373,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"ASDiv-A","model_name":"ATHENA (roberta-large)","metrics":{"Execution Accuracy":"91"},"paper_url":"https://arxiv.org/abs/2311.01036v1","paper_title":"ATHENA: Mathematical Reasoning with Thought Expansion","paper_date":"2023-11-02","code_links":[{"title":"the-jb/athena-math","url":"https://github.com/the-jb/athena-math"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25374,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"ASDiv-A","model_name":"MMOS-DeepSeekMath-7B(0-shot)","metrics":{"Execution Accuracy":"87.6"},"paper_url":"https://arxiv.org/abs/2403.00799v1","paper_title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","paper_date":"2024-02-23","code_links":[{"title":"cyzhh/MMOS","url":"https://github.com/cyzhh/MMOS"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25375,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"ASDiv-A","model_name":"ATHENA (roberta-base)","metrics":{"Execution Accuracy":"86.4"},"paper_url":"https://arxiv.org/abs/2311.01036v1","paper_title":"ATHENA: Mathematical Reasoning with Thought Expansion","paper_date":"2023-11-02","code_links":[{"title":"the-jb/athena-math","url":"https://github.com/the-jb/athena-math"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25376,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"ASDiv-A","model_name":"MMOS-CODE-34B(0-shot)","metrics":{"Execution Accuracy":"85.1"},"paper_url":"https://arxiv.org/abs/2403.00799v1","paper_title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","paper_date":"2024-02-23","code_links":[{"title":"cyzhh/MMOS","url":"https://github.com/cyzhh/MMOS"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25377,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"ASDiv-A","model_name":"OpenMath-CodeLlama-70B (w/ code)","metrics":{"Execution Accuracy":"84.7"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25378,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"ASDiv-A","model_name":"Graph2Tree with RoBERTa","metrics":{"Execution Accuracy":"82.2"},"paper_url":"https://arxiv.org/abs/2103.07191v2","paper_title":"Are NLP Models really able to Solve Simple Math Word Problems?","paper_date":"2021-03-12","code_links":[{"title":"arkilpatel/SVAMP","url":"https://github.com/arkilpatel/SVAMP"},{"title":"debjitpaul/refiner","url":"https://github.com/debjitpaul/refiner"},{"title":"vedantgaur/symbolic-mwp-reasoning","url":"https://github.com/vedantgaur/symbolic-mwp-reasoning"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25379,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"ASDiv-A","model_name":"GTS with RoBERTa","metrics":{"Execution Accuracy":"81.2"},"paper_url":"https://arxiv.org/abs/2103.07191v2","paper_title":"Are NLP Models really able to Solve Simple Math Word Problems?","paper_date":"2021-03-12","code_links":[{"title":"arkilpatel/SVAMP","url":"https://github.com/arkilpatel/SVAMP"},{"title":"debjitpaul/refiner","url":"https://github.com/debjitpaul/refiner"},{"title":"vedantgaur/symbolic-mwp-reasoning","url":"https://github.com/vedantgaur/symbolic-mwp-reasoning"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":25380,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"ASDiv-A","model_name":"MMOS-CODE-7B(0-shot)","metrics":{"Execution Accuracy":"78.6"},"paper_url":"https://arxiv.org/abs/2403.00799v1","paper_title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","paper_date":"2024-02-23","code_links":[{"title":"cyzhh/MMOS","url":"https://github.com/cyzhh/MMOS"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":25381,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"ASDiv-A","model_name":"LSTM Seq2Seq with RoBERTa","metrics":{"Execution Accuracy":"76.9"},"paper_url":"https://arxiv.org/abs/2103.07191v2","paper_title":"Are NLP Models really able to Solve Simple Math Word Problems?","paper_date":"2021-03-12","code_links":[{"title":"arkilpatel/SVAMP","url":"https://github.com/arkilpatel/SVAMP"},{"title":"debjitpaul/refiner","url":"https://github.com/debjitpaul/refiner"},{"title":"vedantgaur/symbolic-mwp-reasoning","url":"https://github.com/vedantgaur/symbolic-mwp-reasoning"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94951,"task":"Math Word Problem Solving","parent_task":null,"dataset":"ASDiv-A","model_name":"ATHENA (roberta-large)","metrics":{"Execution Accuracy":"91"},"paper_url":"https://arxiv.org/abs/2311.01036v1","paper_title":"ATHENA: Mathematical Reasoning with Thought Expansion","paper_date":"2023-11-02","code_links":[{"title":"the-jb/athena-math","url":"https://github.com/the-jb/athena-math"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94952,"task":"Math Word Problem Solving","parent_task":null,"dataset":"ASDiv-A","model_name":"MMOS-DeepSeekMath-7B(0-shot)","metrics":{"Execution Accuracy":"87.6"},"paper_url":"https://arxiv.org/abs/2403.00799v1","paper_title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","paper_date":"2024-02-23","code_links":[{"title":"cyzhh/MMOS","url":"https://github.com/cyzhh/MMOS"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94953,"task":"Math Word Problem Solving","parent_task":null,"dataset":"ASDiv-A","model_name":"ATHENA (roberta-base)","metrics":{"Execution Accuracy":"86.4"},"paper_url":"https://arxiv.org/abs/2311.01036v1","paper_title":"ATHENA: Mathematical Reasoning with Thought Expansion","paper_date":"2023-11-02","code_links":[{"title":"the-jb/athena-math","url":"https://github.com/the-jb/athena-math"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94954,"task":"Math Word Problem Solving","parent_task":null,"dataset":"ASDiv-A","model_name":"MMOS-CODE-34B(0-shot)","metrics":{"Execution Accuracy":"85.1"},"paper_url":"https://arxiv.org/abs/2403.00799v1","paper_title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","paper_date":"2024-02-23","code_links":[{"title":"cyzhh/MMOS","url":"https://github.com/cyzhh/MMOS"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94955,"task":"Math Word Problem Solving","parent_task":null,"dataset":"ASDiv-A","model_name":"OpenMath-CodeLlama-70B (w/ code)","metrics":{"Execution Accuracy":"84.7"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94956,"task":"Math Word Problem Solving","parent_task":null,"dataset":"ASDiv-A","model_name":"Graph2Tree with RoBERTa","metrics":{"Execution Accuracy":"82.2"},"paper_url":"https://arxiv.org/abs/2103.07191v2","paper_title":"Are NLP Models really able to Solve Simple Math Word Problems?","paper_date":"2021-03-12","code_links":[{"title":"arkilpatel/SVAMP","url":"https://github.com/arkilpatel/SVAMP"},{"title":"debjitpaul/refiner","url":"https://github.com/debjitpaul/refiner"},{"title":"vedantgaur/symbolic-mwp-reasoning","url":"https://github.com/vedantgaur/symbolic-mwp-reasoning"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94957,"task":"Math Word Problem Solving","parent_task":null,"dataset":"ASDiv-A","model_name":"GTS with RoBERTa","metrics":{"Execution Accuracy":"81.2"},"paper_url":"https://arxiv.org/abs/2103.07191v2","paper_title":"Are NLP Models really able to Solve Simple Math Word Problems?","paper_date":"2021-03-12","code_links":[{"title":"arkilpatel/SVAMP","url":"https://github.com/arkilpatel/SVAMP"},{"title":"debjitpaul/refiner","url":"https://github.com/debjitpaul/refiner"},{"title":"vedantgaur/symbolic-mwp-reasoning","url":"https://github.com/vedantgaur/symbolic-mwp-reasoning"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":94958,"task":"Math Word Problem Solving","parent_task":null,"dataset":"ASDiv-A","model_name":"MMOS-CODE-7B(0-shot)","metrics":{"Execution Accuracy":"78.6"},"paper_url":"https://arxiv.org/abs/2403.00799v1","paper_title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","paper_date":"2024-02-23","code_links":[{"title":"cyzhh/MMOS","url":"https://github.com/cyzhh/MMOS"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":94959,"task":"Math Word Problem Solving","parent_task":null,"dataset":"ASDiv-A","model_name":"LSTM Seq2Seq with RoBERTa","metrics":{"Execution Accuracy":"76.9"},"paper_url":"https://arxiv.org/abs/2103.07191v2","paper_title":"Are NLP Models really able to Solve Simple Math Word Problems?","paper_date":"2021-03-12","code_links":[{"title":"arkilpatel/SVAMP","url":"https://github.com/arkilpatel/SVAMP"},{"title":"debjitpaul/refiner","url":"https://github.com/debjitpaul/refiner"},{"title":"vedantgaur/symbolic-mwp-reasoning","url":"https://github.com/vedantgaur/symbolic-mwp-reasoning"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112197,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"ASDiv-A","model_name":"ATHENA (roberta-large)","metrics":{"Execution Accuracy":"91"},"paper_url":"https://arxiv.org/abs/2311.01036v1","paper_title":"ATHENA: Mathematical Reasoning with Thought Expansion","paper_date":"2023-11-02","code_links":[{"title":"the-jb/athena-math","url":"https://github.com/the-jb/athena-math"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112198,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"ASDiv-A","model_name":"MMOS-DeepSeekMath-7B(0-shot)","metrics":{"Execution Accuracy":"87.6"},"paper_url":"https://arxiv.org/abs/2403.00799v1","paper_title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","paper_date":"2024-02-23","code_links":[{"title":"cyzhh/MMOS","url":"https://github.com/cyzhh/MMOS"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112199,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"ASDiv-A","model_name":"ATHENA (roberta-base)","metrics":{"Execution Accuracy":"86.4"},"paper_url":"https://arxiv.org/abs/2311.01036v1","paper_title":"ATHENA: Mathematical Reasoning with Thought Expansion","paper_date":"2023-11-02","code_links":[{"title":"the-jb/athena-math","url":"https://github.com/the-jb/athena-math"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112200,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"ASDiv-A","model_name":"MMOS-CODE-34B(0-shot)","metrics":{"Execution Accuracy":"85.1"},"paper_url":"https://arxiv.org/abs/2403.00799v1","paper_title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","paper_date":"2024-02-23","code_links":[{"title":"cyzhh/MMOS","url":"https://github.com/cyzhh/MMOS"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112201,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"ASDiv-A","model_name":"OpenMath-CodeLlama-70B (w/ code)","metrics":{"Execution Accuracy":"84.7"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112202,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"ASDiv-A","model_name":"Graph2Tree with RoBERTa","metrics":{"Execution Accuracy":"82.2"},"paper_url":"https://arxiv.org/abs/2103.07191v2","paper_title":"Are NLP Models really able to Solve Simple Math Word Problems?","paper_date":"2021-03-12","code_links":[{"title":"arkilpatel/SVAMP","url":"https://github.com/arkilpatel/SVAMP"},{"title":"debjitpaul/refiner","url":"https://github.com/debjitpaul/refiner"},{"title":"vedantgaur/symbolic-mwp-reasoning","url":"https://github.com/vedantgaur/symbolic-mwp-reasoning"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112203,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"ASDiv-A","model_name":"GTS with RoBERTa","metrics":{"Execution Accuracy":"81.2"},"paper_url":"https://arxiv.org/abs/2103.07191v2","paper_title":"Are NLP Models really able to Solve Simple Math Word Problems?","paper_date":"2021-03-12","code_links":[{"title":"arkilpatel/SVAMP","url":"https://github.com/arkilpatel/SVAMP"},{"title":"debjitpaul/refiner","url":"https://github.com/debjitpaul/refiner"},{"title":"vedantgaur/symbolic-mwp-reasoning","url":"https://github.com/vedantgaur/symbolic-mwp-reasoning"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":112204,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"ASDiv-A","model_name":"MMOS-CODE-7B(0-shot)","metrics":{"Execution Accuracy":"78.6"},"paper_url":"https://arxiv.org/abs/2403.00799v1","paper_title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","paper_date":"2024-02-23","code_links":[{"title":"cyzhh/MMOS","url":"https://github.com/cyzhh/MMOS"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":112205,"task":"Math Word Problem Solving","parent_task":"Mathematical Question Answering","dataset":"ASDiv-A","model_name":"LSTM Seq2Seq with RoBERTa","metrics":{"Execution Accuracy":"76.9"},"paper_url":"https://arxiv.org/abs/2103.07191v2","paper_title":"Are NLP Models really able to Solve Simple Math Word Problems?","paper_date":"2021-03-12","code_links":[{"title":"arkilpatel/SVAMP","url":"https://github.com/arkilpatel/SVAMP"},{"title":"debjitpaul/refiner","url":"https://github.com/debjitpaul/refiner"},{"title":"vedantgaur/symbolic-mwp-reasoning","url":"https://github.com/vedantgaur/symbolic-mwp-reasoning"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120546,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"ASDiv-A","model_name":"ATHENA (roberta-large)","metrics":{"Execution Accuracy":"91"},"paper_url":"https://arxiv.org/abs/2311.01036v1","paper_title":"ATHENA: Mathematical Reasoning with Thought Expansion","paper_date":"2023-11-02","code_links":[{"title":"the-jb/athena-math","url":"https://github.com/the-jb/athena-math"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120547,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"ASDiv-A","model_name":"MMOS-DeepSeekMath-7B(0-shot)","metrics":{"Execution Accuracy":"87.6"},"paper_url":"https://arxiv.org/abs/2403.00799v1","paper_title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","paper_date":"2024-02-23","code_links":[{"title":"cyzhh/MMOS","url":"https://github.com/cyzhh/MMOS"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120548,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"ASDiv-A","model_name":"ATHENA (roberta-base)","metrics":{"Execution Accuracy":"86.4"},"paper_url":"https://arxiv.org/abs/2311.01036v1","paper_title":"ATHENA: Mathematical Reasoning with Thought Expansion","paper_date":"2023-11-02","code_links":[{"title":"the-jb/athena-math","url":"https://github.com/the-jb/athena-math"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120549,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"ASDiv-A","model_name":"MMOS-CODE-34B(0-shot)","metrics":{"Execution Accuracy":"85.1"},"paper_url":"https://arxiv.org/abs/2403.00799v1","paper_title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","paper_date":"2024-02-23","code_links":[{"title":"cyzhh/MMOS","url":"https://github.com/cyzhh/MMOS"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120550,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"ASDiv-A","model_name":"OpenMath-CodeLlama-70B (w/ code)","metrics":{"Execution Accuracy":"84.7"},"paper_url":"https://arxiv.org/abs/2402.10176v2","paper_title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","paper_date":"2024-02-15","code_links":[{"title":"kipok/nemo-skills","url":"https://github.com/kipok/nemo-skills"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120551,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"ASDiv-A","model_name":"Graph2Tree with RoBERTa","metrics":{"Execution Accuracy":"82.2"},"paper_url":"https://arxiv.org/abs/2103.07191v2","paper_title":"Are NLP Models really able to Solve Simple Math Word Problems?","paper_date":"2021-03-12","code_links":[{"title":"arkilpatel/SVAMP","url":"https://github.com/arkilpatel/SVAMP"},{"title":"debjitpaul/refiner","url":"https://github.com/debjitpaul/refiner"},{"title":"vedantgaur/symbolic-mwp-reasoning","url":"https://github.com/vedantgaur/symbolic-mwp-reasoning"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120552,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"ASDiv-A","model_name":"GTS with RoBERTa","metrics":{"Execution Accuracy":"81.2"},"paper_url":"https://arxiv.org/abs/2103.07191v2","paper_title":"Are NLP Models really able to Solve Simple Math Word Problems?","paper_date":"2021-03-12","code_links":[{"title":"arkilpatel/SVAMP","url":"https://github.com/arkilpatel/SVAMP"},{"title":"debjitpaul/refiner","url":"https://github.com/debjitpaul/refiner"},{"title":"vedantgaur/symbolic-mwp-reasoning","url":"https://github.com/vedantgaur/symbolic-mwp-reasoning"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]},{"id":120553,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"ASDiv-A","model_name":"MMOS-CODE-7B(0-shot)","metrics":{"Execution Accuracy":"78.6"},"paper_url":"https://arxiv.org/abs/2403.00799v1","paper_title":"An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning","paper_date":"2024-02-23","code_links":[{"title":"cyzhh/MMOS","url":"https://github.com/cyzhh/MMOS"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":1,"source":"archive","tags":[]},{"id":120554,"task":"Math Word Problem Solving","parent_task":"Mathematical Reasoning","dataset":"ASDiv-A","model_name":"LSTM Seq2Seq with RoBERTa","metrics":{"Execution Accuracy":"76.9"},"paper_url":"https://arxiv.org/abs/2103.07191v2","paper_title":"Are NLP Models really able to Solve Simple Math Word Problems?","paper_date":"2021-03-12","code_links":[{"title":"arkilpatel/SVAMP","url":"https://github.com/arkilpatel/SVAMP"},{"title":"debjitpaul/refiner","url":"https://github.com/debjitpaul/refiner"},{"title":"vedantgaur/symbolic-mwp-reasoning","url":"https://github.com/vedantgaur/symbolic-mwp-reasoning"}],"metrics_order":"[\"Execution Accuracy\"]","area":"Reasoning","uses_additional_data":0,"source":"archive","tags":[]}]}