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

Mobile UI Control on AndroidWorld

71.6Overall Task Success Rate

GUI-Owl-7B w/ Android Coach

Updated 1mo ago

Evaluation Results

Method	Links
GUI-Owl-7B w/ Android Coach 2026.04		71.6	90.7	58.3	35.1
GUI-Owl-7B w/ GRPO 2026.04		68.1	86.3	55.6	33.3
GUI-Owl-7B w/ PPO 2026.04		68.1	85.2	57.4	33.3
GUI-Owl-7B 2026.04		66.4	-	-	-
GUI-Owl-7B Base Model 2026.04		64.7	84.2	50.9	28.1
GLM-4.5V (106B) 2026.04		57	-	-	-
UI-Venus-Navi-7B 2026.04		49.1	-	-	-
UI-TARS-72B-SFT 2026.04		46.6	-	-	-
Qwen2.5-7B-Instruct-ASL 2025.06		46.3	72.2	32.1	12.5
T3A* (SFT) 2025.06		42.5	72.2	26.8	3.13
T3A 2025.06		41.9	64.9	26.2	14.6
GLM-4.1V-Thinking 2026.04		41.7	-	-	-
UI-TARS-1.5-7B w/ Android Coach 2026.04		41.1	56.3	27.8	17.5
Claude-Sonnet-4 (SoM) 2026.04		41	-	-	-
UI-TARS-72B-DPO 2026.04		40.5	57.4	27.8	10.5
UI-TARS-1.5-7B w/ GRPO 2026.04		38.2	51.9	28.7	12.3
UI-TARS-1.5-7B w/ PPO 2026.04		37.4	50.8	26.9	14
M3A 2025.06		36.6	60.5	20.2	8.3
GPT-4o (SoM) 2026.04		34.5	-	-	-
SOLAR-RL 2026.04		33.7	-	-	-
UI-TARS-7B-SFT 2026.04		33.3	-	-	-
UI-TARS-1.5-7B Base Model 2026.04		32.8	43.7	25.9	10.5
Aguvis-72B 2026.04		26.1	-	-	-
Qwen2.5VL-32B-Instruct 2026.04		25.9	37.2	14.8	10.5
Gemini-Pro-1.5 (SoM) 2026.04		22.8	-	-	-
SeeAct 2025.06		22	34.2	15.5	4.2
OS-Genesis-7B-AW 2026.04		17.8	26.8	11.1	1.8
AgentCPM-GUI-8B 2026.04		17.5	29	5.6	3.5
Qwen2.5-VL-7B-Instruct 2026.04		14.9	23.5	6.5	3.5
T3A* 2025.06		2.5	5.6	0	0