Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-hop Question Answering on MuSiQue (EM, F1, ∆ EM)
Loading...
30
EM
3-Agent Baseline
11.28
16.14
21
25.86
Jun 23, 2026
EM
F1 Score
Delta EM
Updated 1mo ago
Evaluation Results
Method
Method
Links
EM
F1 Score
Delta EM
3-Agent Baseline
Backbone=Qwen2.5-7B-In...
2026.06
30
39.6
16
SDA (rank)
Backbone=Qwen2.5-7B-In...
2026.06
30
38.7
16
PDE
Backbone=Qwen2.5-7B-In...
2026.06
24
34.4
10
CoT De-Polarization
Backbone=Qwen2.5-7B-In...
2026.06
21
30.9
7
NF (No-Filter)
Backbone=Qwen2.5-7B-In...
2026.06
14
21.3
-
PDE-Random
Backbone=Qwen2.5-7B-In...
2026.06
12
19.6
2
Feedback
Search any
task
Search any
task