List your company

Multi-hop Reasoning on FanOutQA

71.84F1 ScoreTOTAL
42.40850.04957.6965.331Oct 8, 2025

Evaluation results

MethodLinks
TOTALModel=Gemini, Prompting Method=TOTAL2025.1071.84
TOTALModel=Claude, Prompting Method=TOTAL2025.1069.99
TOTALModel=GPT, Prompting Method=TOTAL2025.1069.07
CIC + COTModel=Gemini, Prompting Method=CIC + COT2025.1066.97
CICModel=Gemini, Prompting Method=CIC2025.1066.44
CIC + COTModel=GPT, Prompting Method=CIC + COT2025.1066.35
CIC + COTModel=Claude, Prompting Method=CIC + COT2025.1066.29
CICModel=Claude, Prompting Method=CIC2025.1063.74
CICModel=GPT, Prompting Method=CIC2025.1063.39
COTModel=GPT, Prompting Method=COT2025.1049.09
NAÏVEModel=GPT, Prompting Method=NAÏVE2025.1048.77
NAÏVEModel=Claude, Prompting Method=NAÏVE2025.1046.72
NAÏVEModel=Gemini, Prompting Method=NAÏVE2025.1046.54
COTModel=Claude, Prompting Method=COT2025.1045.54
COTModel=Gemini, Prompting Method=COT2025.1043.54