List your company

Web task automation on VisualWebArena full

88.7SRHuman
1.96424.4824769.518Feb 17, 2026Mar 5, 2026Mar 21, 2026Apr 6, 2026Apr 22, 2026May 8, 2026May 24, 2026

Evaluation results

MethodLinks
HumanVisual=–2026.0588.77.7—————
PANDO (Opus 4.6 + GPT-5.2)Visual=mixed2026.0558.39.31152409.11.872.4
SGV (Gemini Flash)Visual=Screenshot + SoM2026.055413.5275392.114.22.345.1
Gemini 3 ProCategory=Proprietary, Teacher for A3-SYNTH=true2026.0449——————
WALT (Sonnet-4 + thinking)Visual=mixed2026.0545.210.5294531.318.32.638.6
GPT-5.2 (M) + SoMVisual=Qwen-2.5VL2026.0538.414.9223210.739.53.461.5
Qwen3.5-27BCategory=Open-weight (base)2026.0437.4——————
Gemini 3.1 Flash L.Category=Proprietary2026.0435——————
A3-Qwen3.5-9BCategory=A3 fine-tuned, Teacher=Gemini 3 Pro2026.0433.9——————
GPT-5.2 (M) + SoMVisual=BLIP-22026.0533.214.9230207.440.84.360.8
GPT-5.2 + SoMVisual=Qwen-2.5VL2026.0531.617.6290181.533.93.764.2
A3-Qwen3.5-4BCategory=A3 fine-tuned, Teacher=Gemini 3 Pro2026.0430.1——————
Qwen3.5-9BCategory=Open-weight (base)2026.0428.5——————
GPT-5.2 + CaptionVisual=Qwen-2.5VL2026.0524.831166388.72.11.910.3
Qwen3.5-4BCategory=Open-weight (base)2026.0424.7——————
WACModel=Qwen3-VL-Plus2026.0224.5——————
ReActModel=Qwen3-VL-Plus2026.0222.7——————
WebDreamerModel=Qwen3-VL-Plus2026.0222.7——————
GPT-5.2 Text-OnlyVisual=Acc. Tree2026.0511.433.1132436.10.37.76.1
A3-Qwen3.5-2BCategory=A3 fine-tuned, Teacher=Gemini 3 Pro2026.047.6——————
Qwen3.5-2BCategory=Open-weight (base)2026.045.3——————