List your company

Multi-hop Reasoning on CRAG

30.08F1 ScoreTOTAL
16.809620.254823.727.1452Oct 8, 2025

Evaluation results

MethodLinks
TOTALModel=Claude, Prompting Method=TOTAL2025.1030.08
TOTALModel=Gemini, Prompting Method=TOTAL2025.1027.71
TOTALModel=GPT, Prompting Method=TOTAL2025.1026.31
CIC + COTModel=Gemini, Prompting Method=CIC + COT2025.1025.77
NAÏVEModel=GPT, Prompting Method=NAÏVE2025.1025.73
CICModel=Gemini, Prompting Method=CIC2025.1025.45
COTModel=Gemini, Prompting Method=COT2025.1024.62
COTModel=GPT, Prompting Method=COT2025.1023.24
CICModel=GPT, Prompting Method=CIC2025.1022.12
NAÏVEModel=Gemini, Prompting Method=NAÏVE2025.1022.03
CIC + COTModel=GPT, Prompting Method=CIC + COT2025.1021.72
NAÏVEModel=Claude, Prompting Method=NAÏVE2025.1020.49
COTModel=Claude, Prompting Method=COT2025.1020.32
CIC + COTModel=Claude, Prompting Method=CIC + COT2025.1018.86
CICModel=Claude, Prompting Method=CIC2025.1017.32