Update app.py

app.py

@@ -39,7 +39,7 @@ After collecting the prompts, we manually classified them by category and got th
 # * Summarization: 1.98%
 
 fig = go.Figure(
-    data=[go.Bar(y=[38.29, 32.94, 15.48, 5.16, 3.77, 1.98, 1.59, 0.6, 0.2]), x=["Generation", "Open QA", "Brainstorming", "Rewrite", "Closed QA", "Summarization", "Chat", "Extraction", "Classification"]],
+    data=[go.Bar(y=[38.29, 32.94, 15.48, 5.16, 3.77, 1.98, 1.59, 0.6, 0.2], x=["Generation", "Open QA", "Brainstorming", "Rewrite", "Closed QA", "Summarization", "Chat", "Extraction", "Classification"])],
 )
 
 description2 = """We intentionally excluded prompts about coding. If you are interested in comparing coding abilities, you can refer to specific benchmarks such as [HumanEval](https://paperswithcode.com/sota/code-generation-on-humaneval).