Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
UI Polishing on UIPolish-Synthetic
Loading...
94
VLM Score
UI2CodeN-9B-RL
3.52
27.01
50.5
73.99
Nov 11, 2025
VLM Score
Updated 27d ago
Evaluation Results
Method
Method
Links
VLM Score
UI2CodeN-9B-RL
Training=RL
2025.11
94
UI2CodeN-9B-SFT
Training=SFT
2025.11
89
GPT-5
Access=Closed-source VLM
2025.11
68
Gemini-2.5-pro
Access=Closed-source VLM
2025.11
68
Doubao-1.6-thinking-250715
Access=Closed-source VLM
2025.11
67
Claude-4-5-Sonnet-thinking
Access=Closed-source VLM
2025.11
66
Claude-4-Sonnet-thinking
Access=Closed-source VLM
2025.11
65
o4-mini
Access=Closed-source VLM
2025.11
65
Claude-3.7-Sonnet-thinking
Access=Closed-source VLM
2025.11
62
Doubao-1.5-thinking-vision
Access=Closed-source VLM
2025.11
61
Qwen3-VL-32B-Instruct
Access=Open-source VLM
2025.11
55
GLM-4.1V-9B-Thinking
Access=Open-source VLM
2025.11
46
Qwen3-VL-8B-Thinking
Access=Open-source VLM
2025.11
41
Kimi-VL-A3B-Instruct
Access=Open-source VLM
2025.11
40
Qwen2.5-VL-72B
Access=Open-source VLM
2025.11
38
MiMo-VL-7B-SFT
Access=Open-source VLM
2025.11
33
MiMo-VL-7B-RL
Access=Open-source VLM
2025.11
30
Kimi-VL-A3B-Thinking
Access=Open-source VLM
2025.11
27
Gemini-2.5-flash
Access=Closed-source VLM
2025.11
24
InternVL3-78B
Access=Open-source VLM
2025.11
15
Qwen2.5-VL-7B
Access=Open-source VLM
2025.11
14
GPT-4o
Access=Closed-source VLM
2025.11
14
InternVL3-9B
Access=Open-source VLM
2025.11
7
Feedback
Search any
task
Search any
task