Model

Phi-3.5 Mini 128k

Test

Voice/dialogue sheets

Scenario

Simple

Run ID

2024-08-26-01J68D8044MWRNMEHTJDDTGJ3Z

Model input

System
You are an editor for novels. Whenever given text, you will extract the contained dialogue as a voice sheet in the following format: Speaker: "Dialogue"
User/Human
“What a curious feeling!” said Alice; “I must be shutting up like a telescope.” “Not like cats!” cried the Mouse, in a shrill, passionate voice. “Would you like cats if you were me?” “Come, there’s no use in crying like that!” said Alice to herself, rather sharply; “I advise you to leave off this minute!”

Model response

AI
Speaker: "What a curious feeling!" Alice Dialogue: "I must be shutting up like a telescope." Speaker: Mouse Dialogue: "Not like cats!" cried the Mouse, in a shrill, passionate voice. "Would you like cats if you were me?" Speaker: Alice Dialogue: "Come, there’s no use in crying like that! I advise you to leave off this minute!" Speaker: Alice Dialogue: "I must be shutting up like a telescope." (Note: The repetition of Alice's quote is confirmed by the context.)
id"gen-GLUe9WOUqZe6587YpPDX6PVc3N7t" 
total_cost0.0000278
upstream_id"chat-b0a0ea7ba49c42b7ad13943ecf0b3fbb" 
created_at"2024-08-26T22:35:02.490805+00:00" Monday, August 26th, 2024 at 10:35:02 PM GMT+00:00
model"microsoft/phi-3.5-mini-128k-instruct" 
app_id182717
streamedtrue
cancelledfalse
provider_name"Azure" 
latency159
moderation_latency(null)
generation_time3541
finish_reason"stop" 
tokens_prompt137
tokens_completion113
native_tokens_prompt136
native_tokens_completion142
num_media_prompt(null)
num_media_completion(null)
origin"https://ncbench.com/" 
usage0.0000278

Evaluation details

Result Evaluator Details Meta Data
Fail Matches Regex
/Alice: ["“”]What a curious feeling! I must be shutting up like a telescope\.["“”]\s+Mouse: ["“”]Not like cats! Would you like cats if you were me\?["“”]\s+Alice: ["“”]Come, there['‘’]s no use in crying like that! I advise you to leave off this minute!["“”]/
 n/a