Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Single-Hop Question Answering on NQ (EM, F1, CEM)
Loading...
47.1
EM
MultiSearch
41.9
43.25
44.6
45.95
May 13, 2026
EM
F1
CEM
Updated 20d ago
Evaluation Results
Method
Method
Links
EM
F1
CEM
MultiSearch
Backbone=3B-Base
2026.05
47.1
56.4
51.4
AutoRefine
2026.05
46.7
53.4
50.2
Search-R1
2026.05
42.1
47.6
46.2
Feedback
Search any
task
Search any
task