{"task":"Code Generation","dataset":"WebApp1k-Duo-React","metric_names":["pass@1"],"rows":[{"id":29536,"task":"Code Generation","parent_task":null,"dataset":"WebApp1k-Duo-React","model_name":"claude-3-5-sonnet","metrics":{"pass@1":"0.679"},"paper_url":"https://arxiv.org/abs/2409.13773v1","paper_title":"A Case Study of Web App Coding with OpenAI Reasoning Models","paper_date":"2024-09-19","code_links":[{"title":"onekq/webapp1k","url":"https://github.com/onekq/webapp1k"}],"metrics_order":"[\"pass@1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":29537,"task":"Code Generation","parent_task":null,"dataset":"WebApp1k-Duo-React","model_name":"o1-mini","metrics":{"pass@1":"0.667"},"paper_url":"https://arxiv.org/abs/2409.13773v1","paper_title":"A Case Study of Web App Coding with OpenAI Reasoning Models","paper_date":"2024-09-19","code_links":[{"title":"onekq/webapp1k","url":"https://github.com/onekq/webapp1k"}],"metrics_order":"[\"pass@1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":29538,"task":"Code Generation","parent_task":null,"dataset":"WebApp1k-Duo-React","model_name":"o1-preview","metrics":{"pass@1":"0.652"},"paper_url":"https://arxiv.org/abs/2409.13773v1","paper_title":"A Case Study of Web App Coding with OpenAI Reasoning Models","paper_date":"2024-09-19","code_links":[{"title":"onekq/webapp1k","url":"https://github.com/onekq/webapp1k"}],"metrics_order":"[\"pass@1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":29539,"task":"Code Generation","parent_task":null,"dataset":"WebApp1k-Duo-React","model_name":"gpt-4o-2024-08-06","metrics":{"pass@1":"0.531"},"paper_url":"https://arxiv.org/abs/2409.13773v1","paper_title":"A Case Study of Web App Coding with OpenAI Reasoning Models","paper_date":"2024-09-19","code_links":[{"title":"onekq/webapp1k","url":"https://github.com/onekq/webapp1k"}],"metrics_order":"[\"pass@1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":29540,"task":"Code Generation","parent_task":null,"dataset":"WebApp1k-Duo-React","model_name":"deepseek-v2.5","metrics":{"pass@1":"0.49"},"paper_url":"https://arxiv.org/abs/2409.13773v1","paper_title":"A Case Study of Web App Coding with OpenAI Reasoning Models","paper_date":"2024-09-19","code_links":[{"title":"onekq/webapp1k","url":"https://github.com/onekq/webapp1k"}],"metrics_order":"[\"pass@1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":29541,"task":"Code Generation","parent_task":null,"dataset":"WebApp1k-Duo-React","model_name":"mistral-large-2","metrics":{"pass@1":"0.449"},"paper_url":"https://arxiv.org/abs/2409.13773v1","paper_title":"A Case Study of Web App Coding with OpenAI Reasoning Models","paper_date":"2024-09-19","code_links":[{"title":"onekq/webapp1k","url":"https://github.com/onekq/webapp1k"}],"metrics_order":"[\"pass@1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]}]}