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

Question Answering on HotPotQA (test) (Custom Metrics: Acc, Prec, Abs(0), Delta)

25.52Accuracy

AFH (Absolute)

-1.02085.869612.7619.6504Oct 1, 2025
Updated 5d ago

Evaluation Results

MethodLinks
2025.10
25.5236.7340.327.93
2025.10
24.3548.2572.860.4
2025.10
23.0634.1739.4524.18
2025.10
20.9860.6787.1464.51
2025.10
20.9653.5981.6367.07
2025.10
17.6851.368253.22
2025.10
17.5834.3759.7643.72
2025.10
16.7260.8492.3875.87
2025.10
13.4447.9782.8141.5
2025.10
7.2566.5496.5436.51
2025.10
0-1000
2025.10
0-1000