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 8 Jul 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 20 Jul 2026.")
                 
             with gr.Tabs(elem_id="inner-tabs", elem_classes="tabs-small") as tabs:
                 with gr.TabItem("Leaderboard"):

report_generation.jsonl

@@ -88,3 +88,7 @@
 {"Model": "Z-AI/GLM-5.2 (Thinking)", "Category": "Open-weight Reasoning", "Overall": 45.8, "Physics": 30.6, "Chemistry": 57.6, "Finance": 25.4, "Consulting": 69.6, "Extraction": 38.2, "Reasoning": 46.5, "Style": 62.1, "Response Characters": 4924, "Input Tokens": 477, "Output Tokens": 12091, "Cost": 8.62}
 {"Model": "Z-AI/GLM-5.2", "Category": "Open-weight Instruct", "Overall": 39.6, "Physics": 21.8, "Chemistry": 45.0, "Finance": 24.8, "Consulting": 66.8, "Extraction": 32.1, "Reasoning": 38.6, "Style": 53.6, "Response Characters": 4867, "Input Tokens": 465, "Output Tokens": 10330, "Cost": 6.69}
 {"Model": "xAI/grok-4.5 (Thinking)", "Category": "Closed-source Reasoning", "Overall": 51.0, "Physics": 33.2, "Chemistry": 69.8, "Finance": 34.3, "Consulting": 66.5, "Extraction": 42.9, "Reasoning": 50.6, "Style": 69.7, "Response Characters": 4509, "Input Tokens": 662, "Output Tokens": 11382, "Cost": 11.14}
+{"Model": "Anthropic/claude-sonnet-5 (Thinking)", "Category": "Closed-source Reasoning", "Overall": 60.4, "Physics": 46.4, "Chemistry": 77.1, "Finance": 45.2, "Consulting": 73.0, "Extraction": 49.0, "Reasoning": 62.3, "Style": 72.9, "Response Characters": 6041, "Input Tokens": 679, "Output Tokens": 19691, "Cost": 31.72}
+{"Model": "OpenAI/GPT-5.6-Sol (xhigh)", "Category": "Closed-source Reasoning", "Overall": 60.4, "Physics": 39.4, "Chemistry": 65.9, "Finance": 62.3, "Consulting": 74.0, "Extraction": 56.4, "Reasoning": 61.3, "Style": 70.0, "Response Characters": 7101, "Input Tokens": 435, "Output Tokens": 15764, "Cost": 76.02}
+{"Model": "OpenAI/GPT-5.6-Sol (xhigh)", "Category": "Closed-source Reasoning", "Overall": 57.2, "Physics": 39.0, "Chemistry": 64.9, "Finance": 54.6, "Consulting": 70.1, "Extraction": 52.3, "Reasoning": 58.5, "Style": 74.6, "Response Characters": 8767, "Input Tokens": 445, "Output Tokens": 19935, "Cost": 48.02}
+{"Model": "OpenAI/GPT-5.6-Sol (xhigh)", "Category": "Closed-source Reasoning", "Overall": 55.3, "Physics": 38.5, "Chemistry": 65.8, "Finance": 46.8, "Consulting": 70.1, "Extraction": 47.3, "Reasoning": 56.4, "Style": 68.2, "Response Characters": 8412, "Input Tokens": 457, "Output Tokens": 23646, "Cost": 22.77}