Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Vision-Language Modeling on MMMUPro
Loading...
53.2
Accuracy
ZPPO
25.744
32.872
40
47.128
Jun 16, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
ZPPO
Model Scale=2B, Prompt...
2026.06
53.2
GRPO
Model Scale=2B, Prompt...
2026.06
49.6
On-Distill
Model Scale=2B, Prompt...
2026.06
49.3
GRPO
Model Scale=2B, Prompt...
2026.06
49.3
On-Distill
Model Scale=2B, Prompt...
2026.06
48.8
Off-Distill
Model Scale=2B, Prompt...
2026.06
47.9
Off-Distill
Model Scale=2B, Prompt...
2026.06
47.4
Qwen3.5
Model Scale=2B, Prompt...
2026.06
46.2
ZPPO
Model Scale=0.8B, Prom...
2026.06
37.6
GRPO
Model Scale=0.8B, Prom...
2026.06
30.5
GRPO
Model Scale=0.8B, Prom...
2026.06
29.9
Off-Distill
Model Scale=0.8B, Prom...
2026.06
29
On-Distill
Model Scale=0.8B, Prom...
2026.06
28.8
On-Distill
Model Scale=0.8B, Prom...
2026.06
28.2
Off-Distill
Model Scale=0.8B, Prom...
2026.06
27.6
Qwen3.5
Model Scale=0.8B, Prom...
2026.06
26.8
Feedback
Search any
task
Search any
task