Skip to content

Commit d98d1bb

Browse files
authored
Update results tables and formatting in README
1 parent ddbb07a commit d98d1bb

File tree

1 file changed

+15
-15
lines changed

1 file changed

+15
-15
lines changed

README.md

Lines changed: 15 additions & 15 deletions
Original file line numberDiff line numberDiff line change
@@ -69,36 +69,36 @@ We will be releasing all the following contents:
6969
Table 1. Main results on ScreenSpot-Pro, ScreenSpot, and ScreenSpot-v2 with **Qwen2-VL** as the backbone. † indicates scores obtained from our own evaluation of the official models on Huggingface.
7070
| Method | Backbone VLM | ScreenSpot-Pro | ScreenSpot | ScreenSpot-v2 |
7171
|------------------|--------------|----------------|------------|----------------|
72-
| **_72B models:_**
72+
| 🏅 **_72B models:_**
7373
| AGUVIS-72B | Qwen2-VL | - | 89.2 | - |
74-
| UGround-V1-72B | Qwen2-VL | 34.5 | **89.4** | - |
75-
| UI-TARS-72B | Qwen2-VL | **38.1** | 88.4 | **90.3** |
76-
| **_7B models:_**
74+
| UGround-V1-72B | Qwen2-VL | 34.5 | 89.4 | - |
75+
| UI-TARS-72B | Qwen2-VL | 38.1 | 88.4 | 90.3 |
76+
| 🏅 **_7B models:_**
7777
| OS-Atlas-7B | Qwen2-VL | 18.9 | 82.5 | 84.1 |
7878
| AGUVIS-7B | Qwen2-VL | 22.9 | 84.4 | 86.0† |
7979
| UGround-V1-7B | Qwen2-VL | 31.1 | 86.3 | 87.6† |
8080
| UI-TARS-7B | Qwen2-VL | 35.7 | **89.5** | **91.6** |
81-
| GUI-Actor-7B | Qwen2-VL | **40.7** | 88.3 | 89.5 |
82-
| GUI-Actor-7B + Verifier | Qwen2-VL | 44.2 | 89.7 | 90.9 |
83-
| **_2B models:_**
81+
| **GUI-Actor-7B** | Qwen2-VL | **40.7** | 88.3 | 89.5 |
82+
| **GUI-Actor-7B + Verifier** | Qwen2-VL | **44.2** | **89.7** | **90.9** |
83+
| 🏅 **_2B models:_**
8484
| UGround-V1-2B | Qwen2-VL | 26.6 | 77.1 | - |
8585
| UI-TARS-2B | Qwen2-VL | 27.7 | 82.3 | 84.7 |
86-
| GUI-Actor-2B | Qwen2-VL | **36.7** | **86.5** | **88.6** |
87-
| GUI-Actor-2B + Verifier | Qwen2-VL | 41.8 | 86.9 | 89.3 |
86+
| **GUI-Actor-2B** | Qwen2-VL | **36.7** | **86.5** | **88.6** |
87+
| **GUI-Actor-2B + Verifier** | Qwen2-VL | **41.8** | **86.9** | **89.3** |
8888

8989
Table 2. Main results on the ScreenSpot-Pro and ScreenSpot-v2 with **Qwen2.5-VL** as the backbone.
9090
| Method | Backbone VLM | ScreenSpot-Pro | ScreenSpot-v2 |
9191
|----------------|---------------|----------------|----------------|
92-
| **_7B models:_**
92+
| 🏅 **_7B models:_**
9393
| Qwen2.5-VL-7B | Qwen2.5-VL | 27.6 | 88.8 |
9494
| Jedi-7B | Qwen2.5-VL | 39.5 | 91.7 |
95-
| GUI-Actor-7B | Qwen2.5-VL | **44.6** | **92.1** |
96-
| GUI-Actor-7B + Verifier | Qwen2.5-VL | 47.7 | 92.5 |
97-
| **_3B models:_**
95+
| **GUI-Actor-7B** | Qwen2.5-VL | **44.6** | **92.1** |
96+
| **GUI-Actor-7B + Verifier** | Qwen2.5-VL | **47.7** | **92.5** |
97+
| 🏅 **_3B models:_**
9898
| Qwen2.5-VL-3B | Qwen2.5-VL | 25.9 | 80.9 |
9999
| Jedi-3B | Qwen2.5-VL | 36.1 | 88.6 |
100-
| GUI-Actor-3B | Qwen2.5-VL | **42.2** | **91.0** |
101-
| GUI-Actor-3B + Verifier | Qwen2.5-VL | 45.9 | 92.4 |
100+
| **GUI-Actor-3B** | Qwen2.5-VL | **42.2** | **91.0** |
101+
| **GUI-Actor-3B + Verifier** | Qwen2.5-VL | **45.9** | **92.4** |
102102

103103
## :rescue_worker_helmet: Installation
104104
1. Clone this repo to your local machine:

0 commit comments

Comments
 (0)