{"task":"Code Generation","dataset":"CodeContests","metric_names":["Test Set pass@1","Test Set pass@5","Val Set pass@1","Val Set pass@5"],"rows":[{"id":758929,"task":"Code Generation","parent_task":null,"dataset":"CodeContests","model_name":"SolidCoder","metrics":{"Test Set pass@1":"77.0"},"paper_url":"https://paperswithcode.com/paper/solidcoder-bridging-the-mental-reality-gap-in-llm-code-generation-through-concrete-execution","paper_title":"SolidCoder: Bridging the Mental-Reality Gap in LLM Code Generation through Concrete Execution","paper_date":"2026-04-20","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]},{"id":29400,"task":"Code Generation","parent_task":null,"dataset":"CodeContests","model_name":"EG-CFG (DeepSeek-V3-0324)","metrics":{"Test Set pass@1":"58.18"},"paper_url":"https://arxiv.org/abs/2506.10948v1","paper_title":"Execution Guided Line-by-Line Code Generation","paper_date":"2025-06-12","code_links":[{"title":"boazlavon/eg_cfg","url":"https://github.com/boazlavon/eg_cfg"}],"metrics_order":"[\"Test Set pass@1\", \"Test Set pass@5\", \"Val Set pass@1\", \"Val Set pass@5\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":29401,"task":"Code Generation","parent_task":null,"dataset":"CodeContests","model_name":"LPW (GPT-4o)","metrics":{"Test Set pass@1":"34.7"},"paper_url":"https://arxiv.org/abs/2411.14503v3","paper_title":"Planning-Driven Programming: A Large Language Model Programming Workflow","paper_date":"2024-11-21","code_links":[{"title":"you68681/lpw","url":"https://github.com/you68681/lpw"}],"metrics_order":"[\"Test Set pass@1\", \"Test Set pass@5\", \"Val Set pass@1\", \"Val Set pass@5\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":29402,"task":"Code Generation","parent_task":null,"dataset":"CodeContests","model_name":"MapCoder (GPT-4)","metrics":{"Test Set pass@1":"28.5","Test Set pass@5":"35.2","Val Set pass@1":"28.5"},"paper_url":"https://arxiv.org/abs/2405.11403v1","paper_title":"MapCoder: Multi-Agent Code Generation for Competitive Problem Solving","paper_date":"2024-05-18","code_links":[{"title":"md-ashraful-pramanik/mapcoder","url":"https://github.com/md-ashraful-pramanik/mapcoder"},{"title":"Luoji-zju/Agents4PLC_release","url":"https://github.com/Luoji-zju/Agents4PLC_release"}],"metrics_order":"[\"Test Set pass@1\", \"Test Set pass@5\", \"Val Set pass@1\", \"Val Set pass@5\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":29403,"task":"Code Generation","parent_task":null,"dataset":"CodeContests","model_name":"CodeSim (GPT4)","metrics":{"Test Set pass@1":"28.4"},"paper_url":"https://arxiv.org/abs/2502.05664v1","paper_title":"CODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debugging","paper_date":"2025-02-08","code_links":[{"title":"kagnlp/CodeGenerator","url":"https://github.com/kagnlp/CodeGenerator"}],"metrics_order":"[\"Test Set pass@1\", \"Test Set pass@5\", \"Val Set pass@1\", \"Val Set pass@5\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":29404,"task":"Code Generation","parent_task":null,"dataset":"CodeContests","model_name":"MoTCoder-15B","metrics":{"Test Set pass@1":"26.34","Val Set pass@1":"20.35"},"paper_url":"https://arxiv.org/abs/2312.15960v5","paper_title":"MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks","paper_date":"2023-12-26","code_links":[{"title":"dvlab-research/motcoder","url":"https://github.com/dvlab-research/motcoder"}],"metrics_order":"[\"Test Set pass@1\", \"Test Set pass@5\", \"Val Set pass@1\", \"Val Set pass@5\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":29405,"task":"Code Generation","parent_task":null,"dataset":"CodeContests","model_name":"MoTCoder-7B-v1.5","metrics":{"Test Set pass@1":"20.77","Val Set pass@1":"16.72"},"paper_url":"https://arxiv.org/abs/2312.15960v5","paper_title":"MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks","paper_date":"2023-12-26","code_links":[{"title":"dvlab-research/motcoder","url":"https://github.com/dvlab-research/motcoder"}],"metrics_order":"[\"Test Set pass@1\", \"Test Set pass@5\", \"Val Set pass@1\", \"Val Set pass@5\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":758997,"task":"Code Generation","parent_task":null,"dataset":"CodeContests","model_name":"SEMAG","metrics":{"Test Set pass@1":"3.3"},"paper_url":"https://paperswithcode.com/paper/semag-self-evolutionary-multi-agent-code-generation","paper_title":"SEMAG: Self-Evolutionary Multi-Agent Code Generation","paper_date":"2026-03-16","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]},{"id":29406,"task":"Code Generation","parent_task":null,"dataset":"CodeContests","model_name":"CodeChain + WizardCoder-15B","metrics":{"Test Set pass@1":"2.35","Test Set pass@5":"3.29","Val Set pass@1":"2.48","Val Set pass@5":"3.30"},"paper_url":"https://arxiv.org/abs/2310.08992v3","paper_title":"CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules","paper_date":"2023-10-13","code_links":[{"title":"SalesforceAIResearch/CodeChain","url":"https://github.com/SalesforceAIResearch/CodeChain"}],"metrics_order":"[\"Test Set pass@1\", \"Test Set pass@5\", \"Val Set pass@1\", \"Val Set pass@5\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":29407,"task":"Code Generation","parent_task":null,"dataset":"CodeContests","model_name":"WizardCoder-15B","metrics":{"Test Set pass@1":"1.11","Test Set pass@5":"3.18","Val Set pass@1":"1.98","Val Set pass@5":"3.27"},"paper_url":"https://arxiv.org/abs/2306.08568v1","paper_title":"WizardCoder: Empowering Code Large Language Models with Evol-Instruct","paper_date":"2023-06-14","code_links":[{"title":"nlpxucan/wizardlm","url":"https://github.com/nlpxucan/wizardlm"},{"title":"nickrosh/evol-teacher","url":"https://github.com/nickrosh/evol-teacher"},{"title":"kyle-lyu/data-efficient-finetuning","url":"https://github.com/kyle-lyu/data-efficient-finetuning"},{"title":"kyle-lyu/codeact","url":"https://github.com/kyle-lyu/codeact"}],"metrics_order":"[\"Test Set pass@1\", \"Test Set pass@5\", \"Val Set pass@1\", \"Val Set pass@5\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":758727,"task":"Code Generation","parent_task":null,"dataset":"CodeContests","model_name":"MARS","metrics":{"Test Set pass@1":"0.624"},"paper_url":"https://paperswithcode.com/paper/mars-multi-specialist-llm-relay-system-for-competitive-programming","paper_title":"MARS: Multi-Specialist LLM Relay System for Competitive Programming","paper_date":"2026-08-24","code_links":[],"metrics_order":null,"area":null,"uses_additional_data":null,"source":"auto","tags":[]}]}