Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on MathVerse VO (Acc@1, Acc@16)
Loading...
73.85
Top-1 Accuracy
Qwen3-VL-8B-Instruct (Teacher)
33.7788
44.1819
54.585
64.9881
May 30, 2026
Top-1 Accuracy
Top-16 Accuracy
Updated 1d ago
Evaluation Results
Method
Method
Links
Top-1 Accuracy
Top-16 Accuracy
Qwen3-VL-8B-Instruct (Teacher)
Model Size=8B
2026.05
73.85
-
VGS On-Policy Distillation
Student Model=Qwen3-VL...
2026.05
71.1
68.53
Standard On-Policy Distillation
Student Model=Qwen3-VL...
2026.05
70.18
68.33
VGS On-Policy Distillation
Student Model=Qwen3-VL...
2026.05
56.19
56.52
Standard On-Policy Distillation
Student Model=Qwen3-VL...
2026.05
54.59
55.76
Qwen3-VL-4B-Instruct (Initial Student)
Model Size=4B
2026.05
53.67
-
Qwen3-VL-2B-Instruct (Initial Student)
Model Size=2B
2026.05
35.32
-
Feedback
Search any
task
Search any
task