Upload 2 files

app.py

@@ -111,7 +111,7 @@ with gr.Blocks(theme=theme) as app:
         with gr.TabItem("Report Generation"):
             with gr.Row():
                 with gr.Column(scale=7):
-                    gr.Markdown("Report Generation Leaderboard: LLMs generate reports with just the prompt, which are then evaluated by gpt-oss-120b (mixed) judge with the lite dataset (160 samples) \nEvaluation and cost estimation last performed on 19 May 2026.")
+                    gr.Markdown("Report Generation Leaderboard: LLMs generate reports with just the prompt, which are then evaluated by gpt-oss-120b (mixed) judge with the lite dataset (160 samples) \nEvaluation and cost estimation last performed on 29 May 2026.")
                 
             with gr.Tabs(elem_id="inner-tabs", elem_classes="tabs-small") as tabs:
                 with gr.TabItem("Leaderboard"):

report_generation.jsonl

@@ -82,3 +82,4 @@
 {"Model": "xAI/grok-4.3", "Category": "Closed-source Reasoning", "Overall": 40.1, "Physics": 25.6, "Chemistry": 57.0, "Finance": 21.1, "Consulting": 56.8, "Extraction": 32.9, "Reasoning": 39.5, "Style": 60.7, "Response Characters": 2520, "Input Tokens": 572, "Output Tokens": 2057, "Cost": 0.94}
 {"Model": "Google/Gemini-3.5-Flash (Thinking)", "Category": "Closed-source Reasoning", "Overall": 56.0, "Physics": 42.7, "Chemistry": 71.5, "Finance": 35.2, "Consulting": 74.8, "Extraction": 51.0, "Reasoning": 56.7, "Style": 66.4, "Response Characters": 9102, "Input Tokens": 479, "Output Tokens": 17344, "Cost": 25.09}
 {"Model": "Google/Gemini-3.5-Flash", "Category": "Closed-source Instruct", "Overall": 54.5, "Physics": 40.3, "Chemistry": 70.9, "Finance": 35.3, "Consulting": 71.6, "Extraction": 50.8, "Reasoning": 56.0, "Style": 64.9, "Response Characters": 8379, "Input Tokens": 479, "Output Tokens": 2593, "Cost": 3.85}
+{"Model": "Anthropic/claude-opus-4.8 (Thinking)", "Category": "Closed-source Reasoning", "Overall": 56.8, "Physics": 38.9, "Chemistry": 73.5, "Finance": 44.8, "Consulting": 70.0, "Extraction": 49.4, "Reasoning": 56.6, "Style": 62.1, "Response Characters": 5125, "Input Tokens": 731, "Output Tokens": 12625, "Cost": 51.08}