Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Local RAG on PopQA
Loading...
33.3
F1 Score
FoldAct-7B
26.02
27.91
29.8
31.69
Dec 28, 2025
F1 Score
EM Score
Updated 4d ago
Evaluation Results
Method
Method
Links
F1 Score
EM Score
FoldAct-7B
consistency loss=false
2025.12
33.3
29.2
FoldAct-7B
consistency loss=true
2025.12
32.9
29
ReSearch-7B
2025.12
32
27.1
SearchR1-7B
RL-training=PPO
2025.12
30.9
27.5
Qwen-7B
few-shot=true
2025.12
30.7
24.4
DeepRes.-7B
2025.12
30.6
25.7
ASearcher-local-7B
2025.12
29.9
25.3
Qwen-7B
few-shot=false
2025.12
26.3
21.4
Feedback
Search any
task
Search any
task