Share your thoughts, 1 month free Claude Pro on usSee more

Action Prediction on AndroidControl Low v2

88.9Pass@1 Step Accuracy

GUI-Libra-8B

Updated 7d ago

Evaluation Results

Method
GUI-Libra-8B 2026.05	88.9	-	-	91.7	-	-	-	-
Mem-W-8B 2026.05	87.94	93.72	89.24	94.22	98.24	94.62	-	-
GPT-5 + UGround 2026.05	86.2	-	-	90	-	-	-	-
GUI-Libra-7B 2026.05	85.2	-	-	90.7	-	-	-	-
Mem-W-4B 2026.05	84.92	90.95	92.58	89.2	93.72	93.72	-	-
Qwen3-VL-32B 2026.05	84.42	89.95	91.83	88.69	92.21	94.17	-	-
UI-Venus-1.5-8B 2026.05	81.66	88.44	91.03	87.19	93.22	94.17	-	-
UI-Venus-1.5-30B-A3B 2026.05	79.65	87.94	87.44	87.44	91.21	91.93	-	-
Qwen3-VL-4B 2026.05	78.9	85.93	90.58	82.4	88.69	93.72	-	-
GPT-4o + UGround 2026.05	78.4	-	-	85.4	-	-	-	-
GPT-4.1 + UGround 2026.05	78.4	-	-	83.2	-	-	-	-
Qwen3-VL-2B 2026.05	77.64	85.18	87	84.92	89.95	93.72	-	-
Qwen3-VL-8B 2026.05	77.6	82.91	90.27	83.2	86.93	94.17	-	-
GUI-Owl-1.5-8B 2026.05	77.14	86.68	88.34	84.42	93.47	92.38	-	-
GPT-5-mini + UGround 2026.05	77.1	-	-	83.2	-	-	-	-
Step-GUI-4B 2026.05	68.84	75.13	88.79	82.16	86.68	94.62	-	-
GLM-4.1V-9B-Thinking 2026.05	67.1	90.2	67.26	73.4	93.22	78.48	-	-
GUI-R1-7B 2026.05	62.3	-	-	72.6	-	-	-	-
GUI-R1-3B 2026.05	55.8	-	-	71.9	-	-	-	-
MAI-UI-2B 2026.05	49.25	64.32	82.51	54.77	68.09	87	-	-
UI-TARS-1.5-7B 2026.05	48.5	71.36	80.27	70.9	89.95	87.44	-	-
Aguvis-7B 2026.05	48	-	-	48.7	-	-	-	-
GPT-4o + UGround-v1-7B 2026.02	-	-	-	-	-	-	78.4	85.4
GPT-4.1 + UGround-v1-7B 2026.02	-	-	-	-	-	-	78.4	83.2
GPT-5-mini + UGround-v1-7B 2026.02	-	-	-	-	-	-	77.1	83.2
GPT-5 + UGround-v1-7B 2026.02	-	-	-	-	-	-	86.2	90
GUI-R1-3B 2026.02	-	-	-	-	-	-	55.8	71.9
GUI-R1-7B 2026.02	-	-	-	-	-	-	62.3	72.6
Aguvis-7B 2026.02	-	-	-	-	-	-	48	48.7
UI-TARS-1.5-7B 2026.02	-	-	-	-	-	-	48.5	70.9
GLM-4.1V-9B-Thinking 2026.02	-	-	-	-	-	-	67.1	73.4
Qwen2.5-VL-32B 2026.02	-	-	-	-	-	-	78.4	85.4
Qwen2.5-VL-72B 2026.02	-	-	-	-	-	-	82.9	90.2
Qwen3-VL-32B 2026.02	-	-	-	-	-	-	83.9	86.9
Qwen2.5-VL-3B 2026.02	-	-	-	-	-	-	71.1	79.2
GUI-Libra-3B 2026.02	-	-	-	-	-	-	85.9	90.5
Qwen2.5-VL-7B 2026.02	-	-	-	-	-	-	67.8	81.7
GUI-Libra-7B 2026.02	-	-	-	-	-	-	85.2	90.7
Qwen3-VL-4B 2026.02	-	-	-	-	-	-	78.9	82.4
GUI-Libra-4B 2026.02	-	-	-	-	-	-	86.4	93
Qwen3-VL-8B 2026.02	-	-	-	-	-	-	77.6	83.2
GUI-Libra-8B 2026.02	-	-	-	-	-	-	88.9	91.7