Update README.md
Browse files
README.md
CHANGED
|
@@ -35,10 +35,10 @@ We follow the standard evaluation protocol and benchmark our model on three chal
|
|
| 35 |
| UGround-v1-72B | 72B | β
| β | 34.5 | β | β |
|
| 36 |
| Qwen2.5-VL-72B-Instruct | 72B | β
| 94.00* | 53.3 | β | 62.2* |
|
| 37 |
| UI-TARS | 72B | β
| 90.3 | 38.1 | β | β |
|
| 38 |
-
| OpenCUA | 7B | β
| 92.3 |
|
| 39 |
| OpenCUA | 32B | β
| 93.4 | 55.3 | 59.6 | 70.2* |
|
| 40 |
| GTA1-2507 (Ours) | 7B | β
| 92.4 <sub>*(β +2.7)*</sub> | 50.1<sub>*(β +8.1)*</sub> | 55.1 <sub>*(β +2.3)*</sub> | 67.7 <sub>*(β +3.5)*</sub> |
|
| 41 |
-
| GTA1
|
| 42 |
| GTA1 (Ours) | 32B | β
| 95.2 <sub>*(β +1.8)*</sub> | 63.6<sub>*(β +8.3)*</sub> | 65.2 <sub>*(β +5.6)*</sub> | 72.2<sub>*(β +2.0)*</sub> |
|
| 43 |
|
| 44 |
> **Note:**
|
|
|
|
| 35 |
| UGround-v1-72B | 72B | β
| β | 34.5 | β | β |
|
| 36 |
| Qwen2.5-VL-72B-Instruct | 72B | β
| 94.00* | 53.3 | β | 62.2* |
|
| 37 |
| UI-TARS | 72B | β
| 90.3 | 38.1 | β | β |
|
| 38 |
+
| OpenCUA | 7B | β
| 92.3 | 50.0 | 55.3 | 68.3* |
|
| 39 |
| OpenCUA | 32B | β
| 93.4 | 55.3 | 59.6 | 70.2* |
|
| 40 |
| GTA1-2507 (Ours) | 7B | β
| 92.4 <sub>*(β +2.7)*</sub> | 50.1<sub>*(β +8.1)*</sub> | 55.1 <sub>*(β +2.3)*</sub> | 67.7 <sub>*(β +3.5)*</sub> |
|
| 41 |
+
| GTA1 (Ours) | 7B | β
| 93.4 <sub>*(β +0.1)*</sub> | 55.5<sub>*(β +5.5)*</sub> | 60.1<sub>*(β +4.8)*</sub> | 68.8<sub>*(β +0.5)*</sub> |
|
| 42 |
| GTA1 (Ours) | 32B | β
| 95.2 <sub>*(β +1.8)*</sub> | 63.6<sub>*(β +8.3)*</sub> | 65.2 <sub>*(β +5.6)*</sub> | 72.2<sub>*(β +2.0)*</sub> |
|
| 43 |
|
| 44 |
> **Note:**
|