List your company

GUI Reasoning on AndroidControl Low

91.8SRUI-TARS-7B
16.50436.05255.675.148Dec 2, 2025Dec 24, 2025Jan 15, 2026Feb 7, 2026Mar 1, 2026Mar 23, 2026Apr 15, 2026

Evaluation results

MethodLinks
UI-TARS-7BModel Type=Open-source, Model Scale=7B2026.0491.8—89.395.2
AgentCPM-GUI-8BModel Type=Open-source, Model Scale=8B2026.0490.2——94.4
Aguvis-7BModel Type=Open-source, Model Scale=7B2026.0489.4——93.8
UI-S1-7BModel Type=Open-source, Model Scale=7B2026.0489.2—89.392.2
UI-Copilot-7BModel Type=Open-source, Model Scale=7B2026.0489.2—88.293.6
OS-Atlas-7BModel Type=Open-source, Model Scale=7B2026.0485.2—8893.6
OS-Atlas-4BModel Type=Open-source, Model Scale=4B2026.0480.6—83.891.9
UI-AGILE-7BModel Type=Open-source, Model Scale=7B2026.0477.6—88.187.7
SeeClickModel Type=Open-source2026.0475—73.493
UI-AGILE-3BModel Type=Open-source, Model Scale=3B2026.0474.3—87.685.4
OS-Genesis-7BModel Type=Open-source, Model Scale=7B2026.0474.2——90.7
UI-R1-7BModel Type=Open-source, Model Scale=7B2026.0469.7—83.786.6
NaviMaster-7BModel Type=Open-source, Model Scale=7B2026.0469.5—93.9—
GUI-R1-7BModel Type=Open-source, Model Scale=7B2026.0466.5—85.485.2
UI-R1-3BModel Type=Open-source, Model Scale=3B2026.0466.4—82.479.2
GUI-R1-3BModel Type=Open-source, Model Scale=3B2026.0464.4—81.683.7
GRPOPrompting=zero-shot2025.1263.8782.1380.15—
Qwen2.5VL-7BModel Type=Open-source, Model Scale=7B2026.0462.5—8783.4
CAPOPrompting=zero-shot2025.1261.4182.2981.19—
QwenVL2.5-3BPrompting=zero-shot2025.1259.3262.0374.07—
Qwen2.5VL-3BModel Type=Open-source, Model Scale=3B2026.0459.3—74.162
Os-Atlas-4BPrompting=zero-shot2025.1240.6264.5871.19—
GPT-4oModel Type=Closed-source2026.0419.4—074.3
Claude-CUModel Type=Closed-source2026.0419.4—074.3