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

Multi-Hop Question Answering on Bamboogle (out-of-domain)

73.8Accuracy

SKILLRL

12.02428.06244.160.138Aug 11, 2025Sep 10, 2025Oct 10, 2025Nov 10, 2025Dec 10, 2025Jan 9, 2026Feb 9, 2026
Updated 2mo ago

Evaluation Results

MethodLinks
2026.02
73.8-
2025.08
73.174.3
2025.08
7172.8
2025.08
64.865.6
2025.08
56.657.6
2026.02
54.4-
2025.08
52.643.2
2025.08
46.653.6
2025.08
4547.2
2026.02
40-
2026.02
36.8-
2025.08
36.528
2026.02
30.4-
2026.02
27.8-
2025.08
24.718.4
2026.02
24-
2026.02
19.2-
2026.02
16.8-
2026.02
14.4-