Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Logical deduction on MineSweeper
Loading...
52
p@1
GiGPO
2.6
15.425
28.25
41.075
Dec 18, 2025
p@1
p@2
p@3
Updated 4d ago
Evaluation Results
Method
Method
Links
p@1
p@2
p@3
GiGPO
Training Strategy=Trai...
2025.12
52
54.9
55.1
RLOO
Training Strategy=Trai...
2025.12
48.8
51.2
51.6
LAMER
Training Strategy=Trai...
2025.12
44.1
66.4
74.4
GRPO
Training Strategy=Trai...
2025.12
36.3
40
40.4
PPO
Training Strategy=Trai...
2025.12
29.7
34.2
35.5
ReAct
Training Strategy=Prom...
2025.12
6.3
7
10.9
Reflexion
Training Strategy=Prom...
2025.12
5.5
7.2
9.8
Zero-shot
Training Strategy=Prom...
2025.12
4.5
6.6
8.6
Feedback
Search any
task
Search any
task