List your company

Question Answering on HotPotQA (test) (Metrics: Acc, TC, TP)

56.34AccuracySearch-R1
25.337633.386341.43549.4837Oct 1, 2025

Evaluation results

MethodLinks
Search-R1inference mode=w/ search tools2025.1056.34314.09
MASH w/ OTCinference mode=w/ search tools2025.1055.421.1432.91
MASH w/ EXPinference mode=w/ search tools2025.1053.781.0732.09
MASH w/ OTC-STinference mode=w/ search tools2025.1053.321.132.55
OTCinference mode=w/ search tools2025.1044.760.8128.64
R1inference mode=w/ search tools2025.1026.53026.53