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

GUI Agent Task on AndroidWorld

80Success Rate

Human

Updated 5d ago

Evaluation Results

Method	Links
Human 2025.05		80
AgentProg 2025.12		78
LAMO-3B 2026.04		77.6
UI-KOBE 2026.05		77.6
MAI-UI-235B-A22B 2026.05		76.7
UI-Ins-7B 2026.04		74.1
Mobile-Agent-v3 2025.12		73.3
UI-TARS-2 2026.03		73.3
Mobile-Agent-V3 2026.04		73.3
MAI-UI-32B 2026.05		73.3
Mobile-Agent-v3 2026.05		73.3
UI-KOBE 2026.05		72.4
MAI-UI-8B 2026.05		70.7
UI-KOBE 2026.05		70.7
Agent S3 2025.12		68.1
Step-GUI-8B 2026.05		67.7
JT-GUIAgentV2 2026.04		67.2
Qwen3.5-plus 2026.05		66.8
DMS-PA-Lite 2026.01		66.4
Mobile-Agent-v3 2025.12		66.4
GUI-Owl-7B 2026.05		66.4
UI-Venus 2026.01		65.9
UI-Venus 2025.12		65.9
UI-Venus-Navi-72B 2026.04		65.9
UI-Venus-72B 2026.05		65.9
Qwen3-VL-32B-Thinking w/ TraceR1 2026.03		64.8
UI-TARS 2025.12		64.2
UI-TARS-1.5 2026.03		64.2
Qwen3-VL-235B-A22B-Instruct 2026.04		63.7
Qwen3-VL-235B-A22B 2026.05		63.7
MobileUse 2026.01		62.9
MobileUse 2025.12		62.9
MobileUse 2026.05		62.9
AppAgentX 2026.05		62.5
Seed1.5-VL 2026.01		62.1
Seed1.5-VL 2026.03		62.1
Qwen3-VL-32B-Thinking 2026.03		61.4
LAMO-3B 2026.04		60.3
V-Droid 2026.01		59.5
V-Droid 2025.12		59.5
V-Droid 2026.05		59.5
Qwen3.5-4B 2026.05		58.6
Qwen3.5-9B 2026.05		57.8
Qwen3-VL-32B 2026.05		57.3
DMS-PA-Lite 2026.01		56
GUI-Owl-7B 2026.01		54.3
Agent-S2 2026.01		54.3
Agent S2 w/ Claude 3.7 Sonnet 2026.03		54.3
Agent-S2 2026.04		54.3
Agent-S2 2026.05		54.3
EAM 2026.05		52.6
OpenAI CUA-o3 2026.03		52.5
OpenAI CUA-o3 2026.04		52.5
EchoTrail-GUI 2026.01		51.7
MobileExplorer 2026.05		50.9
DMS-PA-Lite 2026.01		50.4
Qwen3-VL-8B-Thinking 2026.03		50
MAI-UI-2B 2026.05		49.1
UI-Venus-7B 2026.05		49.1
Qwen3-VL-8B 2026.05		47.6
GUI-explorer 2025.05		47.4
GUI-Explorer 2026.05		47.4
GUI-Explorer 2026.05		47.4
AndroidGen 2026.01		46.8
GPT-5 2026.01		46.6
EchoTrail-GUI 2026.01		46.6
UI-TARS 2026.01		46.6
UI-TARS-72B 2026.04		46.6
UI-Tars-72B 2026.05		46.6
MobileGen 2026.01		45.7
Aria-UITH 2024.12		44.8
Aria-UI 2025.05		44.8
Aria-UI 2026.01		44.8
GPT-4o + Aria-UI 2026.04		44.8
SeeAct-V 2024.10		44
UGround 2026.01		44
DMS-PA-Lite 2026.01		44
ADMIRE(w/Qwen2.5-VL-7B-Instruct) 2026.02		44
MAGNET 2026.01		42.62
MobileGen 2026.01		42.2
GLM-4.1V-9B-Thinking 2025.12		41.7
GLM-4.1V-9B-Thinking 2026.02		41.7
GLM-4.1V-9B-Thinking 2026.05		41.7
GUI-Rewalk 2026.01		41.4
PA-Lite 2026.01		41
PA-Lite 2026.01		41
Claude-Sonnet-4 2026.02		41
Agent-S 2026.01		40.98
M3A 2025.05		40.5
MobileGen 2026.01		40.5
GUI-Shepherd 2026.02		40.5
M3A 2026.05		40.5
Aria-UI 2024.12		39.7
UI-TARS-1.5-7B 2026.01		39.7
M3A 2025.12		39.7
M3A 2026.05		39.7
SE-GA 2026.05		39
PA-Lite 2026.01		38
OS-Genesis 2026.01		37.9
Aguvis 2025.05		37.1

Showing 100 of 188 rows