List your company

Visual Web Agent Navigation on DeepShop

68.7Success RateOpenWebRL-4B w/ OpenWebRL-Judge-8B
9.31624.73340.1555.567Jun 1, 2026

Evaluation results

MethodLinks
OpenWebRL-4B w/ OpenWebRL-Judge-8Bbackbone=4B, # Steps=30, # Tasks=2.2k2026.0668.7
OpenWebRL-8Bbackbone=8B, # Steps=30, # Tasks=2.2k2026.0665.3
OpenWebRL-4Bbackbone=4B, # Steps=30, # Tasks=2.2k2026.0664
Gemini computer-use-preview# Steps=100, # Tasks=–2026.0662
Qwen3-VL-235B-A22B-Thinking# Steps=30, # Tasks=–2026.0656.7
Gemini-3-flash (Axtree)# Steps=100, # Tasks=–2026.0655.3
OpenWebRL-8B-SFTbackbone=8B, # Steps=30, # Tasks=0.9k2026.0650
o3 (SoM)# Steps=100, # Tasks=–2026.0649.7
GPT-5 (SoM)# Steps=100, # Tasks=–2026.0649.1
OpenWebRL-4B-SFTbackbone=4B, # Steps=30, # Tasks=0.4k2026.0648.7
Gemini-3-flash (Axtree)# Steps=30, # Tasks=–2026.0645.1
Qwen3-VL-8B-Thinking# Steps=30, # Tasks=–2026.0644
MolmoWeb-8B# Steps=100, # Tasks=>278.5k2026.0642.3
GPT-5 (Axtree)# Steps=30, # Tasks=–2026.0640.7
MolmoWeb-4B# Steps=100, # Tasks=>278.5k2026.0635.6
Qwen3-VL-4B-Thinking# Steps=30, # Tasks=–2026.0633.3
GLM-4.1V-9B-Thinking# Steps=100, # Tasks=–2026.0632
Fara-7B# Steps=100, # Tasks=>123.2k2026.0626.2
OpenAI computer-use-preview# Steps=100, # Tasks=–2026.0624.7
GPT-4o (SoM)# Steps=100, # Tasks=–2026.0616
UI-TARS-1.5-7B# Steps=100, # Tasks=–2026.0611.6