NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY8E9FRH6DRCP59J42X9W92
Run Details
Model:
Ministral 3 14B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3.4s
Cost:
$0.000076
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
90.48%
Matches word count
(details)
2.63%
Dialogue to Total Word Ratio
(details)
46.5587%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
Molly adjusted her ski mask and grinned at Bill, who was already picking the lock on the back gate of the suburban mansion. "Alright, Bill, you got the lock, I got the plan. Or at least, I got the *idea* of a plan." Bill didn’t look up from his work. "You mean the part where we walk in like we belong, grab all the presents, and leave before the kids even notice?" "Exactly! We’ll be the coolest party guests ever. The *mysterious* ones." Bill finally lifted his head, raising an eyebrow. "Mysterious? More like *suspicious*. You’re wearing a ski mask indoors, Molly. That’s not subtle." "Subtle’s overrated. Besides, who’s gonna stop us? A bunch of kids and their parents? Please. I’ve got my best ‘I’m just here for the cake’ face on." Bill sighed, shaking his head. "You realize we’re breaking into a *children’s party*, right? There’s gonna be balloons, streamers, maybe even a clown." Molly gasped, clutching her chest. "A clown? That’s *worse*. We’ll just have to be extra charming. Maybe even do a little magic trick to distract them." Bill groaned. "You’re gonna pull a rabbit out of your sleeve?" "Only if it’s full of cash. Now come on, let’s go be the best guests they never invited."
created_at
"2026-02-20T19:29:17.825Z"
2/20/2026, 7:29:17 PM
model
"mistralai/ministral-14b-2512"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
179
moderation_latency
(null)
generation_time
3118
tokens_prompt
77
tokens_completion
329
native_tokens_prompt
69
native_tokens_completion
312
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
0.0000762
router
(null)
provider_responses
0
endpoint_id
"0b53717b-9af5-4de3-80af-ebedd2adf981"
id
"800defed83944c368c3129ac94f55d5d"
is_byok
false
latency
179
model_permaslug
"mistralai/ministral-14b-2512"
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771615757-7BZFmvDOGcHF4g0mMHwA"
upstream_id
"800defed83944c368c3129ac94f55d5d"
total_cost
0.0000762
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
90.48%
Matches word count
n/a
neededClean
false
words
210
2.63%
Dialogue to Total Word Ratio
Ratio: 76.19%, Deviation: 13.81%
neededClean
false
wordsTotal
210
wordsDialogue
160
46.5587%