System Prompts
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
System Prompts 41-model
0.915Self-Consistency Score
10
System Prompts Weather
100FSR
9
System Prompts Pirate
100FSR
9
System Prompts OAI
100FSR
9
System Prompts Robot
1FSR
9
20 system prompts
63SFT Accuracy
6
20 system prompts
97.1TF-IDF Accuracy
6