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

Multi-Hop Search-augmented Question Answering on HotpotQA (success rate (%))

38.8Success Rate

Role-Agent

23.09627.17331.2535.327May 29, 2026May 30, 2026Jun 1, 2026Jun 3, 2026Jun 5, 2026Jun 7, 2026Jun 9, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
38.8
2026.06
36.9
2026.06
34.5
2026.05
34.2
2026.05
34
2026.05
33.8
2026.05
32.8
2026.05
32.7
2026.06
32.4
2026.05
32.2
2026.05
31.7
2026.05
31.6
2026.05
28.6
2026.05
28.6
2026.05
28.6
2026.05
28.5
2026.05
27.8
2026.05
27.7
2026.05
27.4
2026.06
27.4
2026.05
24.8
2026.06
23.7