pratikbhavsar commited on
Commit
0c0ca73
·
1 Parent(s): 23236a9

changed model type

Browse files
Files changed (1) hide show
  1. results.csv +1 -1
results.csv CHANGED
@@ -1,6 +1,6 @@
1
  Model,Model Type,Model Output Type,Vendor,Input cost per million token,Output cost per million token,Model Avg,single turn perf,multi turn perf,BFCL_v3_multi_turn_base_multi_func_call,BFCL_v3_multi_turn_composite,tau_long_context,xlam_single_tool_multiple_call,BFCL_v3_multi_turn_miss_param,xlam_multiple_tool_single_call,xlam_tool_miss,BFCL_v3_multi_turn_long_context,BFCL_v3_irrelevance,BFCL_v3_multi_turn_base_single_func_call,xlam_single_tool_single_call,xlam_multiple_tool_multiple_call,BFCL_v3_multi_turn_miss_func,toolace_single_func_call
2
  claude-3-7-sonnet-20250219,Private,Reasoning,Anthropic,3,15,0.953,0.96,0.95,0.92,0.96,1,0.95,0.97,1,0.96,0.94,0.97,0.96,0.99,0.82,0.92,0.975
3
- gemini-2.5-pro-preview-03-25,Private,Normal,Google,1.25,10,0.941,0.93,0.95,0.95,0.97,0.97,0.82,0.95,0.99,0.89,0.92,1,0.93,1,0.84,0.95,1
4
  gemini-2.0-flash-001,Private,Normal,Google,0.15,0.6,0.938,0.95,0.93,0.91,0.94,0.9,0.96,0.92,0.95,0.89,0.91,0.98,0.93,0.97,0.98,0.93,0.965
5
  gemini-2.0-flash-lite-001,Private,Normal,Google,0.075,0.3,0.933,0.96,0.91,0.81,0.98,0.98,0.9,0.91,0.92,0.98,0.86,0.99,0.87,0.97,0.96,0.95,0.975
6
  mistral-small-2503,Open source,Normal,Mistral,0.1,0.3,0.912,0.93,0.89,0.85,0.93,0.86,0.91,0.9,1,0.83,0.81,0.99,0.87,0.99,0.95,0.9,0.975
 
1
  Model,Model Type,Model Output Type,Vendor,Input cost per million token,Output cost per million token,Model Avg,single turn perf,multi turn perf,BFCL_v3_multi_turn_base_multi_func_call,BFCL_v3_multi_turn_composite,tau_long_context,xlam_single_tool_multiple_call,BFCL_v3_multi_turn_miss_param,xlam_multiple_tool_single_call,xlam_tool_miss,BFCL_v3_multi_turn_long_context,BFCL_v3_irrelevance,BFCL_v3_multi_turn_base_single_func_call,xlam_single_tool_single_call,xlam_multiple_tool_multiple_call,BFCL_v3_multi_turn_miss_func,toolace_single_func_call
2
  claude-3-7-sonnet-20250219,Private,Reasoning,Anthropic,3,15,0.953,0.96,0.95,0.92,0.96,1,0.95,0.97,1,0.96,0.94,0.97,0.96,0.99,0.82,0.92,0.975
3
+ gemini-2.5-pro-preview-03-25,Private,Reasoning,Google,1.25,10,0.941,0.93,0.95,0.95,0.97,0.97,0.82,0.95,0.99,0.89,0.92,1,0.93,1,0.84,0.95,1
4
  gemini-2.0-flash-001,Private,Normal,Google,0.15,0.6,0.938,0.95,0.93,0.91,0.94,0.9,0.96,0.92,0.95,0.89,0.91,0.98,0.93,0.97,0.98,0.93,0.965
5
  gemini-2.0-flash-lite-001,Private,Normal,Google,0.075,0.3,0.933,0.96,0.91,0.81,0.98,0.98,0.9,0.91,0.92,0.98,0.86,0.99,0.87,0.97,0.96,0.95,0.975
6
  mistral-small-2503,Open source,Normal,Mistral,0.1,0.3,0.912,0.93,0.89,0.85,0.93,0.86,0.91,0.9,1,0.83,0.81,0.99,0.87,0.99,0.95,0.9,0.975