zhilinw commited on
Commit
c9b5e5b
·
verified ·
1 Parent(s): 96332ed

Upload report_generation.jsonl

Browse files
Files changed (1) hide show
  1. report_generation.jsonl +2 -2
report_generation.jsonl CHANGED
@@ -90,8 +90,8 @@
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}
91
  {"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}
92
  {"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}
93
- {"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}
94
- {"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}
95
  {"Model": "Google/Gemini-3.6-Flash (Thinking)", "Category": "Closed-source Reasoning", "Overall": 57.4, "Physics": 43.0, "Chemistry": 70.1, "Finance": 43.7, "Consulting": 72.6, "Extraction": 52.8, "Reasoning": 58.0, "Style": 67.6, "Response Characters": 8151, "Input Tokens": 479, "Output Tokens": 12776, "Cost": 15.45}
96
  {"Model": "Google/Gemini-3.6-Flash", "Category": "Closed-source Instruct", "Overall": 55.0, "Physics": 38.0, "Chemistry": 68.7, "Finance": 40.3, "Consulting": 73.1, "Extraction": 51.1, "Reasoning": 56.0, "Style": 66.8, "Response Characters": 7698, "Input Tokens": 479, "Output Tokens": 2405, "Cost": 3.0}
97
  {"Model": "Google/Gemini-3.5-Flash-Lite (Thinking)", "Category": "Closed-source Reasoning", "Overall": 51.6, "Physics": 37.3, "Chemistry": 64.9, "Finance": 34.4, "Consulting": 69.8, "Extraction": 45.7, "Reasoning": 53.1, "Style": 62.1, "Response Characters": 5726, "Input Tokens": 479, "Output Tokens": 10959, "Cost": 4.41}
 
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}
91
  {"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}
92
  {"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}
93
+ {"Model": "OpenAI/GPT-5.6-Terra (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}
94
+ {"Model": "OpenAI/GPT-5.6-Luna (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}
95
  {"Model": "Google/Gemini-3.6-Flash (Thinking)", "Category": "Closed-source Reasoning", "Overall": 57.4, "Physics": 43.0, "Chemistry": 70.1, "Finance": 43.7, "Consulting": 72.6, "Extraction": 52.8, "Reasoning": 58.0, "Style": 67.6, "Response Characters": 8151, "Input Tokens": 479, "Output Tokens": 12776, "Cost": 15.45}
96
  {"Model": "Google/Gemini-3.6-Flash", "Category": "Closed-source Instruct", "Overall": 55.0, "Physics": 38.0, "Chemistry": 68.7, "Finance": 40.3, "Consulting": 73.1, "Extraction": 51.1, "Reasoning": 56.0, "Style": 66.8, "Response Characters": 7698, "Input Tokens": 479, "Output Tokens": 2405, "Cost": 3.0}
97
  {"Model": "Google/Gemini-3.5-Flash-Lite (Thinking)", "Category": "Closed-source Reasoning", "Overall": 51.6, "Physics": 37.3, "Chemistry": 64.9, "Finance": 34.4, "Consulting": 69.8, "Extraction": 45.7, "Reasoning": 53.1, "Style": 62.1, "Response Characters": 5726, "Input Tokens": 479, "Output Tokens": 10959, "Cost": 4.41}