61 lines
4.3 KiB
Text
61 lines
4.3 KiB
Text
rank tasks: 42 new (0 done)
|
|
ch19 style rep0 gpt-5-mini → ['Fin-C', 'Fin-B', 'Fin-A'] $0.0059
|
|
ch19 style rep0 kimi-k2.6 → ['Fin-B', 'Fin-A', 'Fin-C'] $0.0312
|
|
ch19 style rep0 gemini-3.1-pro-preview → ['Fin-A', 'Fin-B', 'Fin-C'] $0.0413
|
|
ch19 style rep1 gpt-5-mini → ['Fin-A', 'Fin-B', 'Fin-C'] $0.0057
|
|
ch19 style rep1 kimi-k2.6 → ['Fin-B', 'Fin-A', 'Fin-C'] $0.0352
|
|
ch19 style rep2 gpt-5-mini → ['Fin-B', 'Fin-C', 'Fin-A'] $0.0069
|
|
ch19 style rep2 kimi-k2.6 → ['Fin-A', 'Fin-B', 'Fin-C'] $0.0450
|
|
ch19 fidelity rep0 gpt-5-mini → ['Fin-A', 'Fin-B', 'Fin-C'] $0.0076
|
|
ch19 fidelity rep0 kimi-k2.6 → ['Fin-A', 'Fin-B', 'Fin-C'] $0.0717
|
|
ch19 fidelity rep0 gemini-3.1-pro-preview → ['Fin-A', 'Fin-C', 'Fin-B'] $0.0886
|
|
ch19 fidelity rep1 gpt-5-mini → ['Fin-C', 'Fin-A', 'Fin-B'] $0.0067
|
|
ch19 fidelity rep1 kimi-k2.6 → ['Fin-A', 'Fin-B', 'Fin-C'] $0.0375
|
|
ch19 fidelity rep2 gpt-5-mini → ['Fin-A', 'Fin-B', 'Fin-C'] $0.0069
|
|
ch19 fidelity rep2 kimi-k2.6 → ['Fin-C', 'Fin-A', 'Fin-B'] $0.0615
|
|
ch17 style rep0 gpt-5-mini → ['Fin-C', 'Fin-A', 'Fin-B'] $0.0080
|
|
ch17 style rep0 kimi-k2.6 → ['Fin-C', 'Fin-B', 'Fin-A'] $0.0512
|
|
ch17 style rep0 gemini-3.1-pro-preview → ['Fin-C', 'Fin-B', 'Fin-A'] $0.0583
|
|
ch17 style rep1 gpt-5-mini → ['Fin-C', 'Fin-B', 'Fin-A'] $0.0070
|
|
ch17 style rep1 kimi-k2.6 → ['Fin-C', 'Fin-B', 'Fin-A'] $0.0627
|
|
ch17 style rep2 gpt-5-mini → ['Fin-C', 'Fin-B', 'Fin-A'] $0.0077
|
|
ch17 style rep2 kimi-k2.6 → ['Fin-B', 'Fin-C', 'Fin-A'] $0.0386
|
|
ch17 fidelity rep0 gpt-5-mini → ['Fin-A', 'Fin-B', 'Fin-C'] $0.0072
|
|
ch17 fidelity rep0 kimi-k2.6 → None $0.0000
|
|
ch17 fidelity rep0 gemini-3.1-pro-preview → ['Fin-A', 'Fin-B', 'Fin-C'] $0.0926
|
|
ch17 fidelity rep1 gpt-5-mini → ['Fin-A', 'Fin-B', 'Fin-C'] $0.0062
|
|
ch17 fidelity rep1 kimi-k2.6 → None $0.0781
|
|
ch17 fidelity rep2 gpt-5-mini → ['Fin-A', 'Fin-C', 'Fin-B'] $0.0090
|
|
ch17 fidelity rep2 kimi-k2.6 → ['Fin-C', 'Fin-B', 'Fin-A'] $0.0497
|
|
ch18 style rep0 gpt-5-mini → ['Fin-C', 'Fin-B', 'Fin-A'] $0.0083
|
|
ch18 style rep0 kimi-k2.6 → ['Fin-C', 'Fin-A', 'Fin-B'] $0.0482
|
|
ch18 style rep0 gemini-3.1-pro-preview → ['Fin-C', 'Fin-A', 'Fin-B'] $0.0751
|
|
ch18 style rep1 gpt-5-mini → ['Fin-C', 'Fin-B', 'Fin-A'] $0.0069
|
|
ch18 style rep1 kimi-k2.6 → ['Fin-C', 'Fin-A', 'Fin-B'] $0.0381
|
|
ch18 style rep2 gpt-5-mini → ['Fin-C', 'Fin-B', 'Fin-A'] $0.0069
|
|
ch18 style rep2 kimi-k2.6 → ['Fin-C', 'Fin-A', 'Fin-B'] $0.0488
|
|
ch18 fidelity rep0 gpt-5-mini → ['Fin-C', 'Fin-B', 'Fin-A'] $0.0083
|
|
ch18 fidelity rep0 kimi-k2.6 → ['Fin-A', 'Fin-C', 'Fin-B'] $0.0706
|
|
ch18 fidelity rep0 gemini-3.1-pro-preview → None $0.0989
|
|
ch18 fidelity rep1 gpt-5-mini → ['Fin-A', 'Fin-B', 'Fin-C'] $0.0098
|
|
ch18 fidelity rep1 kimi-k2.6 → ['Fin-A', 'Fin-B', 'Fin-C'] $0.0754
|
|
ch18 fidelity rep2 gpt-5-mini → ['Fin-C', 'Fin-B', 'Fin-A'] $0.0069
|
|
ch18 fidelity rep2 kimi-k2.6 → None $0.0000
|
|
|
|
=== РАНЖИРОВАНИЕ (Borda mean, 2=лучший) ===
|
|
|
|
style: overall {'Fin-C': 1.43, 'Fin-B': 0.95, 'Fin-A': 0.62}
|
|
only gemini-3.1-pro-preview: {'Fin-A': 1, 'Fin-B': 0.67, 'Fin-C': 1.33}
|
|
only gpt-5-mini: {'Fin-C': 1.67, 'Fin-B': 1, 'Fin-A': 0.33}
|
|
only kimi-k2.6: {'Fin-B': 1, 'Fin-A': 0.78, 'Fin-C': 1.22}
|
|
leave-out gemini-3.1-pro-preview: {'Fin-C': 1.44, 'Fin-B': 1, 'Fin-A': 0.56}
|
|
leave-out gpt-5-mini: {'Fin-B': 0.92, 'Fin-A': 0.83, 'Fin-C': 1.25}
|
|
leave-out kimi-k2.6: {'Fin-C': 1.58, 'Fin-B': 0.92, 'Fin-A': 0.5}
|
|
|
|
fidelity: overall {'Fin-A': 1.53, 'Fin-B': 0.71, 'Fin-C': 0.76}
|
|
only gemini-3.1-pro-preview: {'Fin-A': 2, 'Fin-C': 0.5, 'Fin-B': 0.5}
|
|
only gpt-5-mini: {'Fin-A': 1.44, 'Fin-B': 0.78, 'Fin-C': 0.78}
|
|
only kimi-k2.6: {'Fin-A': 1.5, 'Fin-B': 0.67, 'Fin-C': 0.83}
|
|
leave-out gemini-3.1-pro-preview: {'Fin-A': 1.47, 'Fin-B': 0.73, 'Fin-C': 0.8}
|
|
leave-out gpt-5-mini: {'Fin-A': 1.62, 'Fin-B': 0.62, 'Fin-C': 0.75}
|
|
leave-out kimi-k2.6: {'Fin-A': 1.55, 'Fin-B': 0.73, 'Fin-C': 0.73}
|