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 5 Nov 2025.")
+                    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 12 Nov 2025.")
                 
             with gr.Tabs(elem_id="inner-tabs", elem_classes="tabs-small") as tabs:
                 with gr.TabItem("Leaderboard"):

report_generation.jsonl

@@ -34,3 +34,6 @@
 {"Model": "Anthropic/claude-sonnet-4.5", "Category": "Closed-source Instruct", "Overall": 48.1, "Physics": 35.5, "Chemistry": 55.9, "Finance": 34.7, "Consulting": 66.1, "Extraction": 44.8, "Reasoning": 49.9, "Style": 51.2, "Response Characters": 7987, "Input Tokens": 531, "Output Tokens": 2299, "Cost": 5.77}
 {"Model": "MiniMax/M2 (Thinking)", "Category": "Open-weight Reasoning", "Overall": 34.1, "Physics": 22.6, "Chemistry": 38.1, "Finance": 25.2, "Consulting": 50.5, "Extraction": 25.4, "Reasoning": 31.9, "Style": 45.9, "Response Characters": 6485, "Input Tokens": 433, "Output Tokens": 14932, "Cost": 1.09}
 {"Model": "MiniMax/M2", "Category": "Open-weight Instruct", "Overall": 37.7, "Physics": 25.2, "Chemistry": 49.5, "Finance": 25.8, "Consulting": 50.3, "Extraction": 30.1, "Reasoning": 37.3, "Style": 50.9, "Response Characters": 6312, "Input Tokens": 481, "Output Tokens": 8876, "Cost": 0.65}
+{"Model": "MoonshotAI/Kimi-K2-Thinking", "Category": "Open-weight Reasoning", "Overall": 48.9, "Physics": 34.1, "Chemistry": 51.4, "Finance": 40.1, "Consulting": 69.9, "Extraction": 42.4, "Reasoning": 49.3, "Style": 63.5, "Response Characters": 6383, "Input Tokens": 469, "Output Tokens": 14221, "Cost": 5.16}
+{"Model": "DeepSeek-AI/DeepSeek-V3.2-Exp (Thinking)", "Category": "Open-weight Reasoning", "Overall": 41.4, "Physics": 26.2, "Chemistry": 52.4, "Finance": 26.3, "Consulting": 60.8, "Extraction": 31.6, "Reasoning": 41.5, "Style": 56.4, "Response Characters": 5242, "Input Tokens": 458, "Output Tokens": 9938, "Cost": 0.66}
+{"Model": "DeepSeek-AI/DeepSeek-V3.2-Exp", "Category": "Open-weight Instruct", "Overall": 48.2, "Physics": 41.0, "Chemistry": 57.2, "Finance": 32.7, "Consulting": 61.7, "Extraction": 41.9, "Reasoning": 49.3, "Style": 55.5, "Response Characters": 7671, "Input Tokens": 456, "Output Tokens": 2423, "Cost": 0.17}