NC Bench
Overview
About
Tests
Models
Model
Claude 2.1
Test
Dialogue tags
Scenario
Write unattributed dialogue
Run ID
2024-07-15-01J2TTHW6ZPYA6RSMX5P6HA2SG
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 196-word scene with unattributed dialogue set in a small town bakery: "Morning, Abbie! The usual - a dozen assorted cookies and a large coffee to go?" "Make it a latte today, hon. I was up half the night reading the new Janelle Jones mystery. Have you read Foul Play at the Tea House yet? It just came out last week." "No, but I can't wait! Her books always keep me guessing. Was this one any good?" "Oh it was wonderful! I don't want to spoil anything, but let's just say there's a suspicious death during afternoon tea service at a quaint Victorian tearoom, and the amateur sleuth who owns the neighboring knitting shop gets pulled into the investigation." "Oooh, sounds right up my alley. I'll have to pick it up as soon as I'm done with the stack of books on my nightstand! Here are your cookies and latte, by the way. That'll be $8.50 please." "Keep the change, sweetie. Enjoy the new book - let me know what you think once you dive in!" "Will do. See you tomorrow!"
id
"gen-nMIzm1v9b5ptflgfI5LSrI7jIeAt"
total_cost
0.007032
upstream_id
"msg_01Skuu6w2rGVfms2ioJvjKMn"
created_at
"2024-07-15T09:11:39.194991+00:00"
Monday, July 15th, 2024 at 9:11:39 AM GMT+00:00
model
"anthropic/claude-2.1:beta"
app_id
182717
streamed
false
cancelled
false
provider_name
"Anthropic"
latency
14124
moderation_latency
(null)
generation_time
0
finish_reason
"end_turn"
tokens_prompt
69
tokens_completion
244
native_tokens_prompt
78
native_tokens_completion
267
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.007032
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Count dialogue tags
n/a
neededClean
true
dialogueTags
(empty)