Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Question Answering on HotpotQA (GPT-Acc, Contain-Acc.)

76.2GPT Accuracy

GAM-RAG

38.34448.1725867.828Mar 2, 2026
Updated 3mo ago

Evaluation Results

MethodLinks
2026.03
76.274.3
2026.03
74.972.5
2026.03
74.971.9
2026.03
74.271.3
2026.03
66.163.3
2026.03
65.661.8
2026.03
64.362.9
2026.03
58.956.8
2026.03
58.456.2
2026.03
58.160.9
2026.03
55.251.3
2026.03
51.248.3
2026.03
4037.6
2026.03
39.838.2