NC Bench
Overview
About
Tests
Models
Model
Claude 2.0
Test
Dialogue tags
Scenario
Write unattributed dialogue
Run ID
2024-07-15-01J2TTHW68Y0SCF0ZR81SR1D7F
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
Here is a 197 word dialogue scene set in a small town bakery: "Good morning! What can I get started for you today?" "Oh, good morning. I'll take a medium coffee and one of those apple fritters, please." "Excellent choice. We get our apples fresh from Brown's Orchard just down the road. I'll get that fritter warming up for you. And how do you take your coffee?" "Just a splash of cream, thanks." "Coming right up. Hey, did you hear about what happened at the Johnson's place last night?" "No, what happened?" "Apparently their barn went up in flames. No animals were hurt, thank goodness, but the whole barn was destroyed. Such a shame." "How awful! Do they know what caused it?" "Not yet. The fire marshal is investigating today. With all the dry weather we've had lately, it was probably just a spark from something that ignited the hay." "I hope they can rebuild soon. The Johnsons are such nice people." "Here's your coffee and fritter. Let me know if you need anything else!" "Thank you!"
id
"gen-R29jfzfISq8YKTihcJG7zKLjiojr"
total_cost
0.00708
upstream_id
"msg_01DxfQRP43qKZHbJNqXSkXwo"
created_at
"2024-07-15T09:11:25.737792+00:00"
Monday, July 15th, 2024 at 9:11:25 AM GMT+00:00
model
"anthropic/claude-2.0:beta"
app_id
182717
streamed
false
cancelled
false
provider_name
"Anthropic"
latency
16213
moderation_latency
(null)
generation_time
0
finish_reason
"end_turn"
tokens_prompt
69
tokens_completion
232
native_tokens_prompt
78
native_tokens_completion
269
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00708
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Count dialogue tags
n/a
neededClean
true
dialogueTags
(empty)