Fix multiple examples

desktop_env/evaluators/metrics/chrome.py

@@ -65,7 +65,16 @@ def is_expected_installed_extensions(installed_extensions, expected) -> float:
     print("installed_extensions: ")
     print(installed_extensions)
     expected_extensions = expected["expected"]
-    return 1 if expected_extensions == installed_extensions else 0. # must equal, no additional extensions allowed  
+
+    # whether the expected extensions are installed
+    set_expected_extensions = set(expected_extensions)
+    set_installed_extensions = set(installed_extensions)
+
+    if set_expected_extensions.issubset(set_installed_extensions):
+        return 1.
+    else:
+        return 0.
+
 
 def is_expected_tabs(open_tabs: List[Dict[str, str]], rule: Dict[str, Any]) -> float:
     """