List your company

GUI Action Critiquing on BBBench (test)

78.25NDCG@8GPT-5
3.52622.925542.32561.7245May 14, 2026

Evaluation results

MethodLinks
GPT-5Model Category=General VLMs2026.0578.2580.4984.5277.3859.8174.96
BBCritic-7BModel Category=Specialized GUI Policy Models2026.0575.0978.6783.1978.7252.6774.1
GPT-4oModel Category=General VLMs2026.0574.8576.0480.6880.2647.9669.56
Gemini 3 ProModel Category=General VLMs2026.0570.9271.8672.6280.6662.4771.35
BBCritic-3BModel Category=Specialized GUI Policy Models2026.0570.4875.0780.5680.9951.266.1
Qwen2.5-VL-7BModel Category=General VLMs2026.0567.0471.5377.7874.3246.957.62
Claude Sonnet 4.0Model Category=General VLMs2026.0564.5269.8676.7586.947.1766.13
Qwen3-VL-8BModel Category=General VLMs2026.056369.6575.2375.2352.3174.43
Gemini 3 FlashModel Category=General VLMs2026.0555.1355.3255.566.650.6966.28
GAIAModel Category=Specialized GUI Policy Models2026.0546.255.3163.4877.1745.6555.32
MAI-UIModel Category=Specialized GUI Policy Models2026.0543.1151.7561.8366.6240.2361.4
UITARS-1.5-7BModel Category=Specialized GUI Policy Models2026.0538.3547.756.7871.3651.9857.19
UI-VenusModel Category=Specialized GUI Policy Models2026.0536.1245.5557.0360.3946.856.89
GUI-Critic-R1Model Category=Specialized GUI Policy Models2026.056.417.6238.5126.5347.5637.03