Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Mathematical Reasoning on AMC 23 (Accuracy, Pass@1)
Loading...
90
Accuracy
Full CoT SFT
48.4
59.2
70
80.8
Jan 31, 2026
Accuracy
Pass@1
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Pass@1
Full CoT SFT
Model Backbone=R1-Dist...
2026.01
90
-
Segment Selective SFT
Model Backbone=R1-Dist...
2026.01
90
-
R1-Distill-Qwen-7B
Model Backbone=R1-Dist...
2026.01
85
-
Full CoT SFT
Model Backbone=R1-Dist...
2026.01
70
-
Segment Selective SFT
Model Backbone=R1-Dist...
2026.01
60
-
Segment Selective SFT
Model Backbone=Qwen2.5...
2026.01
57.5
-
Full CoT SFT
Model Backbone=Qwen2.5...
2026.01
55
-
R1-Distill-Qwen-1.5B
Model Backbone=R1-Dist...
2026.01
52.5
-
Qwen2.5-7B-Instruct
Model Backbone=Qwen2.5...
2026.01
50
-
R1-Distill-Qwen-1.5B
Model Backbone=R1-Dist...
2026.01
-
73.3
Full CoT SFT
Model Backbone=R1-Dist...
2026.01
-
74.7
Segment Selective SFT
Model Backbone=R1-Dist...
2026.01
-
75.9
Feedback
Search any
task
Search any
task