Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Logical Reasoning on GEM mastermind v1 (test)
Loading...
78.6
Pass@1
Off. + On.
0.6
20.85
41.1
61.35
Jun 29, 2026
Pass@1
Pass@4
Updated 25d ago
Evaluation Results
Method
Method
Links
Pass@1
Pass@4
Off. + On.
Backbone=Qwen3-8B, Pro...
2026.06
78.6
43.1
On-policy Distill.
Backbone=Qwen3-8B, Pro...
2026.06
78
41.8
RL
Backbone=Qwen3-8B, Pro...
2026.06
77.3
38.7
Off-policy Distill.
Backbone=Qwen3-8B, Pro...
2026.06
77.1
41.7
Off-policy Distill.
Backbone=Qwen3-8B, Pro...
2026.06
76.5
39.6
Pre-RL
Backbone=Qwen3-8B, Pro...
2026.06
3.6
0
Feedback
Search any
task
Search any
task