diff --git a/index.html b/index.html index 3996ca1..bcfb23c 100644 --- a/index.html +++ b/index.html @@ -425,335 +425,227 @@

Offline Experiments

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + +

MY ALT TEXT

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
ScreenSpot (Standard Setting)
ModelMobileDesktopWebAverage
TextIcon/WidgetTextIcon/WidgetTextIcon/Widget
InternVL-2-4B9.24.84.64.30.90.14.0
Groma10.32.64.64.35.73.45.2
Qwen-VL9.54.85.75.03.52.45.2
MiniGPT-v28.46.66.22.96.53.45.7
GPT-422.624.520.211.89.28.816.2
GPT-4o20.224.921.123.612.27.818.3
Fuyu41.01.333.03.633.94.419.5
Qwen-GUI52.410.945.95.743.013.628.6
Ferret-UI-Llama8b64.532.345.911.428.311.732.3
Qwen2-VL61.339.352.045.033.021.842.1
CogAgent67.024.074.220.070.428.647.4
SeeClick78.052.072.230.055.732.553.4
OS-Atlas-Base-4B85.758.572.245.782.663.168.0
OmniParser93.957.091.363.681.351.073.0
UGround (Initial)82.860.382.563.680.470.473.3
Iris85.364.286.757.582.671.274.6
ShowUI-G91.669.081.859.083.065.575.0
ShowUI92.375.576.361.181.763.675.1
Molmo-7B-D85.469.079.470.781.365.575.2
UGround-V1-2B (Qwen2-VL)89.472.088.765.781.368.977.7
Molmo-72B92.779.586.164.383.066.078.6
Aguvis-G-7B88.378.288.170.785.774.881.0
OS-Atlas-Base-7B93.072.991.862.990.974.381.0
Aria-UI92.373.893.364.386.576.281.1
Claude (Computer-Use)98.285.679.957.192.284.582.9
Aguvis-7B95.677.793.867.188.375.283.0
Project Mariner84.0
CogAgent-9B-2024122085.4
UGround-V1-7B (Qwen2-VL)93.079.993.876.490.984.086.3
AGUVIS-72B94.585.295.477.991.385.988.4
UGround-V1-72B (Qwen2-VL)94.183.494.985.790.487.989.4
Grounding ModelMobileDesktopWebAverage
TextIcon/WidgetTextIcon/WidgetTextIcon/Widget
GPT-422.624.520.211.89.28.816.2
GPT-4o20.224.921.123.612.27.818.3
MiniGPT-v28.46.66.22.96.53.45.7
Groma10.32.64.64.35.73.45.2
Fuyu41.01.333.03.633.94.419.5
Qwen-VL9.54.85.75.03.52.45.2
SeeClick78.052.072.230.055.732.553.4
Qwen-GUI52.410.945.95.743.013.628.6
UGround-V182.860.382.563.680.470.473.3
Qwen2-VL61.339.352.045.033.021.842.1
Aguvis-G-7B88.378.288.170.785.774.881.0
Aguvis-7B95.677.793.867.188.375.283.0
OS-Atlas-Base-4B85.758.572.245.782.663.168.0
OS-Atlas-Base-7B93.072.991.862.990.974.381.0
ShowUI-G91.669.081.859.083.065.575.0
ShowUI92.375.576.361.181.763.675.1
Iris85.364.286.757.582.671.274.6
Aria-UI92.373.893.364.386.576.281.1
UGround-V1-2B (Qwen2-VL)89.472.088.765.781.368.977.7
UGround-V1-7B (Qwen2-VL)93.079.993.876.490.984.086.3
@@ -789,7 +681,7 @@

Offline Experiments

- + @@ -799,7 +691,7 @@

Offline Experiments

- + @@ -830,7 +722,7 @@

Offline Experiments

- + @@ -879,18 +771,6 @@

Offline Experiments

- - - - - - - - - - - -
48.8
UGround (Initial)UGround-V1 90.1 70.3 87.1 75.6

GPT-4o

GPT-4o
Qwen-VL 21.3 21.4 38.5
UGround (Initial)UGround-V1 93.4 76.9 92.8 73.3 84.0
UGround-V1-72B (Qwen2-VL)94.579.993.875.088.775.284.5
@@ -928,7 +808,7 @@

Offline Experiments

25.6 - +

Image
(SeeAct-V)
@@ -940,14 +820,14 @@

Offline Experiments

29.6 - UGround (Initial) + UGround-V1 45.1 44.7 44.6 44.8 -
GPT-4o +
GPT-4o SeeClick 32.1 33.1 @@ -955,30 +835,12 @@

Offline Experiments

32.9 - UGround (Initial) + UGround-V1 47.7 46.0 46.6 46.8 - - - - UGround-V1-2B (Qwen2-VL) - 48.6 - 47.6 - 47.7 - 48.0 - - - - - UGround-V1-7B (Qwen2-VL) - 50.7 - 48.1 - 48.5 - 49.1 - @@ -1006,7 +868,7 @@

Offline Experiments

55.0 - +

Image
@@ -1018,33 +880,21 @@

Offline Experiments

47.2 - UGround (Initial) + UGround-V1 46.2 58.0 -
GPT-4o +
GPT-4o SeeClick 41.8 52.8 - UGround (Initial) + UGround-V1 48.4 62.4 - - - UGround-V1-2B (Qwen2-VL) - 50.0 - 65.0 - - - - UGround-V1-7B (Qwen2-VL) - 49.8 - 66.2 - @@ -1071,7 +921,7 @@

Offline Experiments

17.0 - +

Image
@@ -1082,28 +932,18 @@

Offline Experiments

28.9 - UGround (Initial) + UGround-V1 31.1 -
GPT-4o +
GPT-4o SeeClick 29.6 - UGround (Initial) + UGround-V1 32.8 - - - UGround-V1-2B (Qwen2-VL) - 32.9 - - - - UGround-V1-7B (Qwen2-VL) - 34.0 - @@ -1145,7 +985,7 @@

Online Experiments

(SeeAct-V)
GPT-4 -
UGround (Initial) +
UGround-V1 50.7 23.1 @@ -1185,7 +1025,7 @@

Online Experiments

(SeeAct-V)
GPT-4 -
UGround (Initial) +
UGround-V1 31.0