NC Bench
Overview
About
Tests
Models
Model
Claude 2.0
Test
Dialogue tags
Scenario
Write unattributed dialogue
Run ID
2024-07-15-01J2TTHW68ZKYSPN6FGERM06CH
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 scene with unattributed dialogue set in a small town bakery: "Good morning! What can I get started for you today?" "Oh, I don't know. Everything looks so delicious. What do you recommend?" "Well, our apple turnovers just came out of the oven, so they're nice and warm. We also have some fresh cinnamon rolls with a cream cheese icing that are to die for." "Mmm, those both sound amazing. I'll take one of each of those to go please. Oh, and can I also get a large coffee with cream and sugar?" "Absolutely! Let me grab those for you. Would you like your coffee in one of our reusable mugs? We sell them for only $3 and you get 10 cents off each time you bring it back." "What a great idea. I'll take a mug too. I'm always looking for ways to reduce waste." "Wonderful! I'll get this all packaged up for you. Your total today is $8.90." "Thank you so much! The smells in here are incredible. I can't wait to dig into these treats!" "Our pleasure! Enjoy, and have a great rest of your day!"
id
"gen-zYyaG7g9DnLPqnku6lU5raSKssXp"
total_cost
0.007248
upstream_id
"msg_015WAWM9crniTDDQ7jNyijHh"
created_at
"2024-07-15T09:12:01.142428+00:00"
Monday, July 15th, 2024 at 9:12:01 AM GMT+00:00
model
"anthropic/claude-2.0:beta"
app_id
182717
streamed
false
cancelled
false
provider_name
"Anthropic"
latency
13860
moderation_latency
(null)
generation_time
0
finish_reason
"end_turn"
tokens_prompt
69
tokens_completion
250
native_tokens_prompt
78
native_tokens_completion
276
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.007248
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Count dialogue tags
n/a
neededClean
true
dialogueTags
(empty)