Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

ChattyChef

Benchmarks

Task NameDataset NameSOTA ResultTrend
User Intent DetectionChattyChef (test)
Micro F178.3
18
Response GenerationChattyChef (test)
BLEU5.4
6
Instruction State TrackingChattyChef (test)
WordMatch79
1
Instruction State TrackingChattyChef (val)
WordMatch0.82
1
Showing 4 of 4 rows