zhilinw commited on
Commit
cd972cc
·
verified ·
1 Parent(s): 2f6b76b

Upload 2 files

Browse files
Files changed (2) hide show
  1. app.py +1 -1
  2. report_generation.jsonl +1 -0
app.py CHANGED
@@ -111,7 +111,7 @@ with gr.Blocks(theme=theme) as app:
111
  with gr.TabItem("Report Generation"):
112
  with gr.Row():
113
  with gr.Column(scale=7):
114
- 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 17 Jun 2026.")
115
 
116
  with gr.Tabs(elem_id="inner-tabs", elem_classes="tabs-small") as tabs:
117
  with gr.TabItem("Leaderboard"):
 
111
  with gr.TabItem("Report Generation"):
112
  with gr.Row():
113
  with gr.Column(scale=7):
114
+ 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.")
115
 
116
  with gr.Tabs(elem_id="inner-tabs", elem_classes="tabs-small") as tabs:
117
  with gr.TabItem("Leaderboard"):
report_generation.jsonl CHANGED
@@ -87,3 +87,4 @@
87
  {"Model": "MiniMax/MiniMax-M3", "Category": "Open-weight Instruct", "Overall": 39.2, "Physics": 18.7, "Chemistry": 43.7, "Finance": 31.8, "Consulting": 62.4, "Extraction": 33.2, "Reasoning": 36.9, "Style": 53.6, "Response Characters": 6827, "Input Tokens": 621, "Output Tokens": 18799, "Cost": 3.64}
88
  {"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}
89
  {"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}
 
 
87
  {"Model": "MiniMax/MiniMax-M3", "Category": "Open-weight Instruct", "Overall": 39.2, "Physics": 18.7, "Chemistry": 43.7, "Finance": 31.8, "Consulting": 62.4, "Extraction": 33.2, "Reasoning": 36.9, "Style": 53.6, "Response Characters": 6827, "Input Tokens": 621, "Output Tokens": 18799, "Cost": 3.64}
88
  {"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}
89
  {"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}
90
+ {"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}