cyberosa commited on
Commit
4435ba7
·
1 Parent(s): b3c6bad

updated accuracy of prediction offline

Browse files
Files changed (1) hide show
  1. formatted_data.csv +1 -1
formatted_data.csv CHANGED
@@ -12,6 +12,7 @@ prediction-online,gpt-4o-2024-08-06,0.7507418397626113,253,337,2484.083086053412
12
  prediction-offline-sme,gpt-4o-2024-08-06,0.7485207100591716,253,338,1381.3727810650887,0.0173823668639053
13
  prediction-offline-sme,gpt-4-0125-preview,0.7484848484848485,247,330,1416.8484848484848,0.0181692121212121
14
  prediction-request-reasoning,gpt-4-0125-preview,0.7483221476510067,223,298,1980.7281879194632,0.0256767449664429
 
15
  prediction-online,claude-3-5-sonnet-20240620,0.7441176470588236,253,340,2774.755882352941,0.0100005970588235
16
  prediction-online-sme,gpt-4o-2024-08-06,0.7430340557275542,240,323,3147.260061919505,0.0363173684210526
17
  prediction-online,claude-3-sonnet-20240229,0.7411764705882353,252,340,2832.7617647058823,0.0095903911764705
@@ -23,7 +24,6 @@ prediction-url-cot,claude-3-5-sonnet-20240620,0.7286135693215339,247,339,14794.7
23
  prediction-offline,claude-2,0.7201834862385321,157,218,779.4770642201835,0.0068916697247706
24
  prediction-online,databricks/dbrx-instruct:nitro,0.7173252279635258,236,329,2696.0607902735564,0.0024264547112461
25
  superforcaster,gpt-4-0125-preview,0.7169230769230769,233,325,2143.230769230769,0.0222704615384615
26
- prediction-offline,gpt-4o-2024-08-06,0.7164179104477612,240,335,732.0776119402985,0.0081607761194029
27
  prediction-request-rag,gpt-4-0125-preview,0.7161716171617162,217,303,1240.980198019802,0.013809207920792
28
  prediction-online,gpt-4-0125-preview,0.713855421686747,237,332,1549.8524096385545,0.0172735843373493
29
  prediction-offline,databricks/dbrx-instruct:nitro,0.7118055555555556,205,288,755.9895833333334,0.0006803906249999
 
12
  prediction-offline-sme,gpt-4o-2024-08-06,0.7485207100591716,253,338,1381.3727810650887,0.0173823668639053
13
  prediction-offline-sme,gpt-4-0125-preview,0.7484848484848485,247,330,1416.8484848484848,0.0181692121212121
14
  prediction-request-reasoning,gpt-4-0125-preview,0.7483221476510067,223,298,1980.7281879194632,0.0256767449664429
15
+ prediction-offline,gpt-4o-2024-08-06,0.746268656716418,240,335,732.0776119402985,0.0081607761194029
16
  prediction-online,claude-3-5-sonnet-20240620,0.7441176470588236,253,340,2774.755882352941,0.0100005970588235
17
  prediction-online-sme,gpt-4o-2024-08-06,0.7430340557275542,240,323,3147.260061919505,0.0363173684210526
18
  prediction-online,claude-3-sonnet-20240229,0.7411764705882353,252,340,2832.7617647058823,0.0095903911764705
 
24
  prediction-offline,claude-2,0.7201834862385321,157,218,779.4770642201835,0.0068916697247706
25
  prediction-online,databricks/dbrx-instruct:nitro,0.7173252279635258,236,329,2696.0607902735564,0.0024264547112461
26
  superforcaster,gpt-4-0125-preview,0.7169230769230769,233,325,2143.230769230769,0.0222704615384615
 
27
  prediction-request-rag,gpt-4-0125-preview,0.7161716171617162,217,303,1240.980198019802,0.013809207920792
28
  prediction-online,gpt-4-0125-preview,0.713855421686747,237,332,1549.8524096385545,0.0172735843373493
29
  prediction-offline,databricks/dbrx-instruct:nitro,0.7118055555555556,205,288,755.9895833333334,0.0006803906249999