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

End-to-end question-answering on HotPotQA (test)

0.464EM

INTRA

0.337120.370060.4030.43594May 7, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.05
0.464
2026.05
0.434
2026.05
0.419
2026.05
0.416
2026.05
0.407
2026.05
0.405
2026.05
0.403
2026.05
0.37
2026.05
0.342