ResearchBenchmarksTask Planning on Daily Life v1 (test)Follow97.36F1 (n)Direct30.893648.149365.40582.6607May 29, 2024Evaluation ResultsMethodMethodLinksF1 (n)F1 (l)Token Count (k)DirectLLM=GPT 4-turboLLM=GPT 4-turbo2024.0597.3684.583.37SGCLLM=GPT 4-turboLLM=GPT 4-turbo2024.0597.3585.763.16SGCLLM=Baichuan2 13BLLM=Baichuan2 13B2024.0562.3136.693.53DirectLLM=Baichuan2 13BLLM=Baichuan2 13B2024.0533.459.523.72