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

Multi-doc QA on HotpotQA

45Accuracy

Dense

22.6428.44534.2540.055Jul 29, 2025
Updated 19d ago

Evaluation Results

MethodLinks
2025.07
450
2025.07
430
2025.07
4116.12
2025.07
4016.2
2025.07
37.50
2025.07
3616.51
2025.07
3615.82
2025.07
3215.7
2025.07
29.215.5
2025.07
2915.75
2025.07
28.516.22
2025.07
28.216.51
2025.07
27.814.8
2025.07
2416.02
2025.07
23.515.8