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

Multi-hop Question Answering on MuSiQue (F1, Token Usage, Compression)

68.98F1 Score

OrgAgent

9.221624.735840.2555.7642Apr 1, 2026
Updated 17d ago

Evaluation Results

MethodLinks
2026.04
68.9811,40837.1159.94
2026.04
57.5812,04618.9752.22
2026.04
51.282,778--
2026.04
50.3128,479--
2026.04
48.425,209--
2026.04
37.982,687--
2026.04
32.5912,322123.9976.04
2026.04
14.5551,425--
2026.04
11.522,370--