Added the Model Comparison assistant for blind comparisons of two models (#1009)

Co-authored-by: Thorsten Sommer <SommerEngineering@users.noreply.github.com>

app/MindWork AI Studio/Assistants/ModelComparison/ModelComparisonSignificance.cs

@@ -0,0 +1,22 @@
+namespace AIStudio.Assistants.ModelComparison;
+
+/// <summary>
+/// Whether the runs decided so far say which of two models is better, see ModelComparisonWinShare.
+/// </summary>
+public enum ModelComparisonSignificance
+{
+    /// <summary>
+    /// Too few runs, or too even a result, to tell yet.
+    /// </summary>
+    NOT_YET_CLEAR,
+
+    /// <summary>
+    /// The model wins clearly more often than it loses.
+    /// </summary>
+    CLEARLY_BETTER,
+
+    /// <summary>
+    /// The model loses clearly more often than it wins.
+    /// </summary>
+    CLEARLY_WORSE,
+}