Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Short-form Question Answering on PopQA (test)
Loading...
36.34
Exact Match
VSPO + PRS_short
7.376
14.8955
22.415
29.9345
Dec 8, 2025
Exact Match
Updated 4d ago
Evaluation Results
Method
Method
Links
Exact Match
VSPO + PRS_short
Backbone=Qwen2.5-3B-In...
2025.12
36.34
GRPO + PRS_short
Backbone=Qwen2.5-3B-In...
2025.12
35.62
PPO + PRS_short
Backbone=Qwen2.5-3B-In...
2025.12
35.62
SFT
Backbone=Qwen2.5-3B-In...
2025.12
10.4
Untrained
Backbone=Qwen2.5-3B-In...
2025.12
8.49
Feedback
Search any
task
Search any
task