NC Bench
Overview
About
Tests
Models
Model
GPT-4o, May 13th (temp=0)
Test
Dialogue tags
Scenario
Write unattributed dialogue
Run ID
2024-07-14-01J2SKDYN2ZFGVFXWPY08YRX3V
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 missing cat?" "Missing? I thought she just let it roam around." "Not this time. She swears someone took it." "Who would steal a cat in this town? Everyone knows everyone." "That's what makes it so strange. She found a note on her porch." "A note? What did it say?" "Something like, 'If you want to see Whiskers again, bring a dozen of your famous apple pies to the old mill.'" "You're kidding. That sounds like a bad movie plot." "I know, right? But Mrs. Thompson is beside herself. She came in here this morning, ordered a dozen pies, and left in a hurry." "Did she say anything else?" "Just that she hoped it was a prank. But she looked really worried." "Poor Mrs. Thompson. Whiskers is like her child." "Exactly. And you know how she is about her pies. She wouldn't just give them away." "Do you think we should do something? Maybe follow her to the mill?" "Maybe. But what if it's dangerous?" "Then we call the sheriff. But we can't just sit here and do nothing." "Alright, let's finish up here and head over. If nothing else, we can keep an eye on her." "Agreed. Let's hope it's just a prank."
id
"gen-aYdM9n9tSC6lW51e3d95jJPpjMLH"
total_cost
0.004525
upstream_id
"chatcmpl-9l1LwQWODWTNG8ecV9tHEmPhT9XWP"
created_at
"2024-07-14T21:47:28.849184+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
4189
moderation_latency
554
generation_time
0
finish_reason
"stop"
tokens_prompt
69
tokens_completion
281
native_tokens_prompt
68
native_tokens_completion
279
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.004525
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)