Add community evaluation results for ScreenSpot-Pro

This PR adds community-provided evaluation results for the following benchmarks:

- **[ScreenSpot-Pro](https://huggingface.co/datasets/likaixin/ScreenSpot-Pro?eval_result=mPLUG/GUI-Owl-32B&leaderboard_task_id=overall&leaderboard_base_model=false)**

These results were extracted from Table 2 of the [paper](https://huggingface.co/papers/2508.15144). This is based on the new [evaluation results feature](https://huggingface.co/docs/hub/eval-results).

*Note: This is an automated PR. Please review the evaluation results before merging.*

.eval_results/screenspot-pro.yaml

@@ -0,0 +1,7 @@
+- dataset:
+    id: likaixin/ScreenSpot-Pro
+    task_id: overall
+  value: 58.0
+  source:
+    url: https://arxiv.org/abs/2508.15144
+    name: Paper (Table 2)