leaderboard_data/human.csv

Organization,Method,Model,DR,EPR(Micro/Macro),LPR(Micro/Macro),C-LPR,FPR
NJU,ReAct (zero-shot),DeepSeek-V3,36.4,29.5 / 0.65,35.2 / 16.2,0.38,0
NJU,ReAct (zero-shot),GPT-4o,96.1,50.5 / 0,72.4 / 32.5,0,0
NJU,ReAct (one-shot),DeepSeek-V3,55.2,57.3 / 2.59,64.6 / 44.2,1.71,2.59
NJU,ReAct (one-shot),GPT-4o,69.5,46.3 / 0,63.6 / 46.8,0,0
NJU,NeSy Planning,DeepSeek-V3,51.9,53.2 / 52.5,47.0 / 37.6,46.5,37.0
NJU,NeSy Planning,GPT-4o,45.4,50.1 / 45.4,40.9 / 29.8,38.5,27.9
NJU,NeSy Planning,Qwen3-8B,42.8,47.4 / 42.2,36.2 / 27.2,34.4,25.3
NJU,NeSy Planning,Llama3.1-8B,25.9,25.8 / 24.0,22.3 / 12.3,20.5,11.0
NJU,NeSy Planning,Mistral-7B,37.6,38.2 / 37.6,32.7 / 18.8,32.2,18.8
NJU,TTG (oracle),DeepSeek-V3,9.09,12.8 / 2.59,7.65 / 5.19,2.39,1.29
NJU,LLM-Modulo*,DeepSeek-V3,61.6,90.2 / 2.59,75.9 / 51.2,2.75,2.59
NJU,LLM-Modulo*,GPT-4o,91.5,87.2 / 3.24,92.9 / 66.2,2.87,3.24
NJU,LLM-Modulo*,Qwen3-8B,35.0,75.3 / 0.0,61.6 / 19.4,0.0,0.0
NJU,LLM-Modulo*,Llama3.1-8B,19.4,74.1 / 0.0,43.4 / 5.19,0.0,0.0
NJU,LLM-Modulo*,Mistral-7B,3.24,92.2 / 0.0,31.4 / 4.54,0.0,0.0
NJU,NeSy Planning*,DeepSeek-V3,58.4,59.6 / 57.7,53.8 / 46.1,52.0,45.4
NJU,NeSy Planning*,GPT-4o,52.6,46.9 / 42.9,47.6 / 40.9,43.9,40.9
NJU,NeSy Planning*,Qwen3-8B,53.2,55.1 / 54.5,48.0 / 42.8,47.6,40.9
NJU,NeSy Planning*,Mistral-7B,40.9,42.8 / 42.8,37.7 / 28.5,37.7,27.9
NJU,NeSy Planning*,Llama3.1-8B,29.2,29.1 / 26.6,25.4 / 20.1,23.4,19.4