Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Reasoning accuracy on PRONTOQA 4-hop
Loading...
85
Accuracy
AVI
50.68
59.59
68.5
77.41
May 17, 2025
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
AVI
Model=Qwen 8B
2025.05
85
AVI
Model=Qwen 4B
2025.05
72
No Correction
Model=Qwen 8B
2025.05
65
Self Correction
Model=Qwen 4B
2025.05
60
Self Correction
Model=Qwen 8B
2025.05
58
No Correction
Model=Qwen 4B
2025.05
52
Feedback
Search any
task
Search any
task