List your company

Multi-hop Reasoning on MuSiQue (F1)

73.3F1 ScoreTOTAL
21.019234.592148.16561.7379Oct 8, 2025

Evaluation results

MethodLinks
TOTALModel=Claude, Prompting Method=TOTAL2025.1073.3
TOTALModel=Gemini, Prompting Method=TOTAL2025.1072.86
CIC + COTModel=Gemini, Prompting Method=CIC + COT2025.1067.17
CICModel=Gemini, Prompting Method=CIC2025.1066.54
TOTALModel=GPT, Prompting Method=TOTAL2025.1066.38
CIC + COTModel=GPT, Prompting Method=CIC + COT2025.1065.11
CIC + COTModel=Claude, Prompting Method=CIC + COT2025.1065.07
CICModel=Claude, Prompting Method=CIC2025.1063.87
CICModel=GPT, Prompting Method=CIC2025.1063.79
NAÏVEModel=GPT, Prompting Method=NAÏVE2025.1032.43
COTModel=GPT, Prompting Method=COT2025.1032.39
COTModel=Claude, Prompting Method=COT2025.1028.1
NAÏVEModel=Claude, Prompting Method=NAÏVE2025.1027.57
NAÏVEModel=Gemini, Prompting Method=NAÏVE2025.1025.48
COTModel=Gemini, Prompting Method=COT2025.1023.03