List your company

Short-term planning on GUI-Act-Web

94.54Type Success RateSSL-7B
54.562464.941275.3285.6988Jan 30, 2026

Evaluation results

MethodLinks
SSL-7Bmode=Post-Training, training=standard RLVR on Mix-3K2026.0194.5489.2587.23
RL-Continous-7Bmode=Post-Training, training=standard RLVR on Mix-3K2026.0194.1589.2586.46
GUI-R1-7Bmode=Post-Training2026.0190.8588.0680.31
RL-Binary-7Bmode=Post-Training, training=standard RLVR on Mix-3K2026.0190.7888.0680.31
GUI-R1-3Bmode=Post-Training2026.0189.8687.4276.31
QwenVL2.5-7B*mode=Post-Training, SFT=Mix-3K2026.0187.6684.7779.89
Os-Atlas-7Bmode=Post-Training2026.0186.9575.6157.02
QwenVL2.5-7Bmode=Zero Shot2026.0186.5984.3978.63
RL-Continous-3Bmode=Post-Training, training=standard RLVR on Mix-3K2026.0186.3885.4972.69
SSL-3Bmode=Post-Training, training=standard RLVR on Mix-3K2026.0185.7787.5285.22
RL-Binary-3Bmode=Post-Training, training=standard RLVR on Mix-3K2026.0182.8483.1975.15
Os-Atlas-4Bmode=Post-Training2026.0179.2258.5742.62
GPT-4omode=Zero Shot2026.0177.0945.0241.84
QwenVL2.5-3B*mode=Post-Training, SFT=Mix-3K2026.0176.9566.3461.69
UI-R1-3Bmode=Post-Training2026.0175.8979.4367.31
QwenVL2.5-3Bmode=Zero Shot2026.0156.164.2855.61