Share your thoughts, 1 month free Claude Pro on usSee more

Inquire-driven GUI Navigation on InquireBench English

6.7SR

GUI-Owl

Updated 1mo ago

Evaluation Results

Method	Links
GUI-Owl 2025.08		6.7	2.2	0.58
Gemini-2.5-pro 2025.08		6.3	-	-
UI-R1-3B 2025.08		6.3	6.3	0.73
InquireMobile 2025.08		6.3	5.3	0.65
InquireMobile 2025.08		5.3	55.8	0.72
Qwen2.5-VL-72B 2025.08		4.2	-	-
GPT-4o-0806 2025.08		4.2	-	-
Claude-3.5-Sonnet v2 2025.08		4.2	-	-
Gemini-2.5-pro 2025.08		4.2	-	-
Claude-3.5-Sonnet v2 2025.08		4.2	-	-
UI-R1-3B-E 2025.08		3.2	2.1	0.54
Qwen2.5-VL-3B 2025.08		1.1	3.2	0.42
InquireMobile 2025.08		1.1	37.9	0.27
GPT-4o-0806 2025.08		1	-	-
Qwen2.5-VL-72B 2025.08		0	-	-
GUI-R1-3B 2025.08		0	1.1	0.37