Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Sudoku Solving on Sudoku
Loading...
100
Success Rate (pass@1)
GPT-OSS-120B
12.12
34.935
57.75
80.565
Jan 29, 2026
Jan 30, 2026
Success Rate (pass@1)
Updated 4d ago
Evaluation Results
Method
Method
Links
Success Rate (pass@1)
GPT-OSS-120B
2026.01
100
GPT-5-nano
2026.01
100
Qwen2.5-3B-It + Evolving Stage
2026.01
97
Scout-PPO
2026.01
85
SSL
Backbone=Qwen2.5, Mode...
2026.01
45.4
RL-Continuous
Backbone=Qwen2.5, Mode...
2026.01
45
RL-Binary
Backbone=Qwen2.5, Mode...
2026.01
44.7
SSL
Backbone=Qwen2.5, Mode...
2026.01
31
RL-Continuous
Backbone=Qwen2.5, Mode...
2026.01
17.3
RL-Binary
Backbone=Qwen2.5, Mode...
2026.01
15.5
Feedback
Search any
task
Search any
task