NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-07-19-01J35T4CZ1K7AGAHEQBZ39SB65
Run Details
Model:
Mistral Large
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
8.0s
Cost:
$0.009120
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
2.01%
Matches word count
(details)
14.97%
Dialogue to Total Word Ratio
(details)
8.4911%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
In the heart of the city, under the neon glow of a blink-and-you'll-miss-it diner, Molly and Bill huddled over a blueprint, their eyes gleaming with mischief. The blueprint was not of a bank or a high-security vault, but of a children's party venue, complete with a bounce house and a coterie of clowns. "Look at this, Bill," Molly said, her finger tracing a path from the entrance to the gift table laden with brightly wrapped presents. "We'll be in and out before they can say 'pin the tail on the donkey'." Bill, a man of few words, grunted in agreement, his gaze fixed on the clown quarters. "Clowns," he muttered, a shudder running through his large frame. "I hate clowns." Molly chuckled, her eyes sparkling with amusement. "You'd rather face a pack of guard dogs than a few harmless clowns?" "Any day," Bill replied, his voice barely a whisper. Molly patted his hand, her laughter subsiding. "Don't worry, Bill. We'll avoid the clowns. We're after the presents, remember?" As the night deepened, their plan took shape. They would slip in as the party wound down, grab the gifts, and vanish into the night. It was a simple plan, but then again, the best ones usually were. And in the world of Molly and Bill, even the simplest plans had a knack for going delightfully awry.
id
"gen-QyeSK8IREsDGLSoGmY9OXjJsEQxq"
total_cost
0.00912
upstream_id
"7540d947ca814de681e1db38ad4783c9"
created_at
"2024-07-19T15:35:31.582355+00:00"
7/19/2024, 3:35:31 PM
model
"mistralai/mistral-large"
app_id
182717
streamed
false
cancelled
false
provider_name
"Mistral"
latency
7942
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
309
native_tokens_prompt
78
native_tokens_completion
354
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00912
Evaluation details
Result
Evaluator
Details
Meta Data
2.01%
Matches word count
n/a
neededClean
false
words
225
14.97%
Dialogue to Total Word Ratio
Ratio: 21.74%, Deviation: 11.74%
neededClean
false
wordsTotal
230
wordsDialogue
50
8.4911%