NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-08-01KGYXKPVG1FRFA2WM9FDDC53W
Run Details
Model:
Mistral Small Creative
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
2.0s
Cost:
$0.000112
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
27.17%
Matches word count
(details)
0.16%
Dialogue to Total Word Ratio
(details)
13.6642%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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
The backseat of Bill’s stolen ice cream truck smelled like expired sprinkles and regret. Molly adjusted her clown nose—*the perfect disguise*—while Bill fiddled with a bag of half-melted lollipops. “You’re sure this is the right party?” Molly asked, squinting at the pastel balloons tied to the mailbox. “Because if we rob the wrong six-year-old’s birthday, I’m blaming you.” Bill popped a lollipop into his mouth. “Positive. Kid’s dad is *that* tech guy—you know, the one who invented the app that makes your phone cry when you ignore it? Presents’ll be top-tier. Maybe even a drone.” Molly groaned. “A *drone*? Bill, we’re stealing My Little Pony merch, not joining the CIA.” “Hey, drones are *useful*. We could use it to case future jobs. Or deliver pizzas. Flexible career path.” She snatched the lollipop from his mouth. “Focus. We go in, grab the loot, and get out before the piñata explodes. No talking to the kids, no eating the cake, and *definitely* no letting them draw on you with washable markers again.” Bill rubbed his arm where a permanent “Mr. Bill” was still faintly visible. “Fine. But if I see a *good* piñata, I’m taking it.” Molly sighed. “You’re a menace.” “And you love me.” “Debatable.” She kicked open the truck door. “Let’s go steal some *Barbie Dreamhouse* real estate.”
created_at
"2026-02-08T15:23:36.150336+00:00"
2/8/2026, 3:23:36 PM
model
"mistralai/mistral-small-creative-20251216"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
241
moderation_latency
(null)
generation_time
1145
tokens_prompt
61
tokens_completion
331
native_tokens_prompt
69
native_tokens_completion
350
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.0001119
router
(null)
provider_responses
0
id
"2220e248f4694228aa4d1beb046e3ba5"
status
200
is_byok
false
latency
241
endpoint_id
"0118a65e-79f9-48b0-924e-38c4a41378e1"
provider_name
"Mistral"
model_permaslug
"mistralai/mistral-small-creative-20251216"
api_type
"completions"
id
"gen-1770564213-6S1AdHaUaz53rGnFDHKp"
upstream_id
"2220e248f4694228aa4d1beb046e3ba5"
total_cost
0.0001119
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
27.17%
Matches word count
n/a
neededClean
false
words
219
0.16%
Dialogue to Total Word Ratio
Ratio: 65.92%, Deviation: 15.92%
neededClean
false
wordsTotal
223
wordsDialogue
147
13.6642%