Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Vision-Language Modeling on AI2D
Loading...
85.3
Accuracy
ZPPO
64.812
70.131
75.45
80.769
Jun 16, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
ZPPO
Model Scale=2B, Prompt...
2026.06
85.3
GRPO
Model Scale=2B, Prompt...
2026.06
83.8
GRPO
Model Scale=2B, Prompt...
2026.06
83.5
On-Distill
Model Scale=2B, Prompt...
2026.06
83.4
Off-Distill
Model Scale=2B, Prompt...
2026.06
82.9
On-Distill
Model Scale=2B, Prompt...
2026.06
82.6
Off-Distill
Model Scale=2B, Prompt...
2026.06
82.5
Qwen3.5
Model Scale=2B, Prompt...
2026.06
81.9
ZPPO
Model Scale=0.8B, Prom...
2026.06
76.5
GRPO
Model Scale=0.8B, Prom...
2026.06
71.2
GRPO
Model Scale=0.8B, Prom...
2026.06
69.5
On-Distill
Model Scale=0.8B, Prom...
2026.06
68.6
On-Distill
Model Scale=0.8B, Prom...
2026.06
67.6
Off-Distill
Model Scale=0.8B, Prom...
2026.06
66.7
Off-Distill
Model Scale=0.8B, Prom...
2026.06
66.3
Qwen3.5
Model Scale=0.8B, Prom...
2026.06
65.6
Feedback
Search any
task
Search any
task