Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Vision-Language Modeling on VBlind
Loading...
60.5
Accuracy
ZPPO
40.74
45.87
51
56.13
Jun 16, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
ZPPO
Model Scale=2B, Prompt...
2026.06
60.5
GRPO
Model Scale=2B, Prompt...
2026.06
57
GRPO
Model Scale=2B, Prompt...
2026.06
56.5
On-Distill
Model Scale=2B, Prompt...
2026.06
55.6
Qwen3.5
Model Scale=2B, Prompt...
2026.06
55.2
On-Distill
Model Scale=2B, Prompt...
2026.06
54.9
Off-Distill
Model Scale=2B, Prompt...
2026.06
54.6
Off-Distill
Model Scale=2B, Prompt...
2026.06
53.7
ZPPO
Model Scale=0.8B, Prom...
2026.06
44.7
GRPO
Model Scale=0.8B, Prom...
2026.06
43.6
GRPO
Model Scale=0.8B, Prom...
2026.06
43.2
Qwen3.5
Model Scale=0.8B, Prom...
2026.06
42.8
On-Distill
Model Scale=0.8B, Prom...
2026.06
42.3
Off-Distill
Model Scale=0.8B, Prom...
2026.06
42.2
Off-Distill
Model Scale=0.8B, Prom...
2026.06
41.8
On-Distill
Model Scale=0.8B, Prom...
2026.06
41.5
Feedback
Search any
task
Search any
task