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

Multi-hop QA on 2WikiMultihopQA

66.2F1 Score

TaSR-RAG

-0.67216.68934.0551.411Feb 28, 2026Mar 1, 2026Mar 3, 2026Mar 5, 2026Mar 6, 2026Mar 8, 2026Mar 10, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
66.251.8--
2026.03
65.645.9--
2026.03
63.655.5--
2026.02
62.3553.80.930.32
2026.02
59.1750.20.370.15
2026.03
51.542.1--
51.4443.91.240.34
2026.02
50.0741.90.550.28
2026.03
47.713.5--
2026.02
45.2135.91.120.29
2026.03
38.530.9--
2026.03
38.219.7--
2026.03
37.830.5--
2026.03
37.224.5--
2026.03
32.125.1--
2026.03
30.112.6--
2026.03
29.122.7--
2026.03
26.220.5--
2026.03
23.916.7--
2026.03
21.314.9--
2026.03
19.615.3--
2026.03
15.110.8--
2026.03
1.91.6--