Our new X account is live! Follow @wizwand_team for updates

GUI Grounding on Screenspot v1

97.07Mobile Text Accuracy

Claude 4 Sonnet CU

Updated 4d ago

Evaluation Results

Method	Links
Claude 4 Sonnet CU 2026.02		97.07	79.48	81.44	64.29	92.61	82.52	84.75
Qwen3-VL-32B 2026.02		96.34	85.59	96.91	87.86	90.87	90.78	91.67
Qwen3-VL-8B 2026.02		95.24	79.91	94.85	81.43	92.17	83.5	88.44
Ovis2.5SFT 2026.02		95.24	78.6	94.85	85	92.61	83.01	88.6
Ovis2.5S-RF++ 2026.02		95.24	79.04	94.85	84.29	92.61	83.5	88.68
GUI-Actor-7B 2026.02		94.9	82.1	91.8	80	91.3	85.4	88.3
UI-TARS-72B 2026.02		94.9	82.5	89.7	88.6	88.7	85	88.4
Ovis2.5S-RLOO 2026.02		94.87	79.04	94.85	85	92.17	82.52	88.44
Ovis2.5S-GRPO 2026.02		94.51	79.04	94.85	85	92.61	83.01	88.52
UI-TARS-72B 2026.02		94.14	82.53	95.36	85	90.87	83.5	88.92
MFT 2026.02		93.4	82.8	96.4	84.3	90.8	89.4	89.2
UI-TARS 1.5-7B 2026.02		92.67	77.73	93.81	71.43	86.52	77.18	84.2
UI-TARS-7B 2026.02		92.31	85.15	90.72	84.29	88.7	85.92	88.21
Claude 3.7 Sonnet CU 2026.02		88.28	73.36	79.9	62.86	90.87	80.58	80.74
GPT-4o 2026.02		20.2	24.9	21.1	23.6	12.2	7.8	18.3