NC Bench
Overview
About
Tests
Models
Model
Claude 2.1
Test
Dialogue tags
Scenario
Write unattributed dialogue
Run ID
2024-07-15-01J2TTKQSBRKQGA2A07RHSTCFE
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 187-word scene with unattributed dialogue set in a small town bakery: "Morning, Abby! The usual today?" "Actually, I'll take two cranberry scones instead of my usual lemon poppyseed muffin. I'm meeting my friend Vera for our Saturday coffee date." "Two cranberry scones coming right up! Tell Vera I said hello." "Will do. Oh, before I forget to ask in all the catching up Vera and I will be doing, has that special order cake for the Johnsons' anniversary party been picked up yet?" "Not yet. They won't be by to get it until this afternoon, before the party." "Got it. I know Vera will want to know if it turned out nicely. She was so thrilled they ordered that beautiful three-tier cake with the edible gold accents." "It's one of my best yet! I'll be sure to save a slice for you both to try tomorrow.” “You’re the best, Maggie. No one makes better baked goods in this town than you do."
id
"gen-Oe2BTFGq087JKV3Rbt8hiJoizTOw"
total_cost
0.006504
upstream_id
"msg_01Cq3a6MAK6ZDzFYaWvDXr16"
created_at
"2024-07-15T09:12:20.651234+00:00"
Monday, July 15th, 2024 at 9:12:20 AM GMT+00:00
model
"anthropic/claude-2.1:beta"
app_id
182717
streamed
false
cancelled
false
provider_name
"Anthropic"
latency
13278
moderation_latency
(null)
generation_time
0
finish_reason
"end_turn"
tokens_prompt
69
tokens_completion
219
native_tokens_prompt
78
native_tokens_completion
245
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.006504
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Count dialogue tags
n/a
neededClean
true
dialogueTags
(empty)