NC Bench
Overview
About
Tests
Models
Model
GPT-4o, May 13th (temp=0)
Test
Dialogue tags
Scenario
Write unattributed dialogue
Run ID
2024-07-14-01J2SKDYN1B2W22YDV6A1HZ6P9
Model input
User/Human
You are an expert novel writer in the cozy mystery genre. Write a scene of about 200 words, with dialogue between two characters. The dialogue should be unattributed, meaning the speaker is not explicitly mentioned. The scene should be set in a small town bakery. Only return the story, nothing else.
Model response
Messages
Meta
AI
"Did you hear about Mrs. Thompson's cat?" "Her cat? No, what happened?" "Gone. Disappeared without a trace." "That's strange. She always kept it indoors." "Exactly. And you know what else? I found a tuft of fur behind the bakery this morning." "You're kidding. Do you think it could be related?" "Maybe. Mrs. Thompson said she heard strange noises last night." "Like what?" "Scratching and a low growl. She thought it was just raccoons." "Raccoons don't growl like that. Did she call the police?" "She did, but they said there's not much they can do about a missing cat." "Typical. Did you see anything unusual when you found the fur?" "Just a few paw prints, but they were too big for a cat." "Could it be a dog?" "Possibly, but it doesn't explain the growling." "True. Maybe we should look around after closing." "Good idea. We can start where I found the fur and see if there are any more clues." "Alright. Meet you here at eight?" "Eight it is. And bring a flashlight." "Got it. Let's hope we find something that helps Mrs. Thompson." "Agreed. Poor woman, she's been through enough already." "Yes, she has. See you tonight." "See you then."
id
"gen-uIGwmhjMBXQWHUIdZhBGMfXDWxhm"
total_cost
0.00463
upstream_id
"chatcmpl-9l1LwBqnKcGacNw29zQTlwY5tCNPX"
created_at
"2024-07-14T21:47:28.443326+00:00"
Sunday, July 14th, 2024 at 9:47:28 PM GMT+00:00
model
"openai/gpt-4o-2024-05-13"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
3931
moderation_latency
201
generation_time
0
finish_reason
"stop"
tokens_prompt
69
tokens_completion
289
native_tokens_prompt
68
native_tokens_completion
286
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00463
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)