{"task":"Benchmarking","dataset":"CloudEval-YAML","metric_names":["ACC"],"rows":[{"id":75767,"task":"Benchmarking","parent_task":null,"dataset":"CloudEval-YAML","model_name":"GPT-4 Turbo","metrics":{"ACC":"0.561"},"paper_url":"https://arxiv.org/abs/2401.06786v1","paper_title":"CloudEval-YAML: A Practical Benchmark for Cloud Configuration Generation","paper_date":"2023-11-10","code_links":[{"title":"alibaba/cloudeval-yaml","url":"https://github.com/alibaba/cloudeval-yaml"}],"metrics_order":"[\"ACC\"]","area":"Robots","uses_additional_data":0,"source":"archive","tags":[]},{"id":116067,"task":"Benchmarking","parent_task":"Data-free Knowledge Distillation","dataset":"CloudEval-YAML","model_name":"GPT-4 Turbo","metrics":{"ACC":"0.561"},"paper_url":"https://arxiv.org/abs/2401.06786v1","paper_title":"CloudEval-YAML: A Practical Benchmark for Cloud Configuration Generation","paper_date":"2023-11-10","code_links":[{"title":"alibaba/cloudeval-yaml","url":"https://github.com/alibaba/cloudeval-yaml"}],"metrics_order":"[\"ACC\"]","area":"Robots","uses_additional_data":0,"source":"archive","tags":[]},{"id":148982,"task":"Benchmarking","parent_task":"Data-free Knowledge Distillation","dataset":"CloudEval-YAML","model_name":"GPT-4 Turbo","metrics":{"ACC":"0.561"},"paper_url":"https://arxiv.org/abs/2401.06786v1","paper_title":"CloudEval-YAML: A Practical Benchmark for Cloud Configuration Generation","paper_date":"2023-11-10","code_links":[{"title":"alibaba/cloudeval-yaml","url":"https://github.com/alibaba/cloudeval-yaml"}],"metrics_order":"[\"ACC\"]","area":"Robots","uses_additional_data":0,"source":"archive","tags":[]}]}