NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHYB5T3J2SWV9C8G650H6HVW
Run Details
Model:
Ministral 3 8B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2.3s
Cost:
$0.000062
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0004%
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
The neon glow of a neon "Happy Birthday!" sign flickered outside the glass as Molly adjusted her mask, her fingers twitching with nervous energy. "Alright, Bill, we’re in. The cake’s got more frosting than a bank vault’s got gold bars. This is gonna be easier than robbing a library." Bill, already crouched by the front door, grinned through his own mask. "Oh, you’ve got it all wrong, Molly. This ain’t about the cake—it’s about the *presents*. You ever seen a kid’s room after a birthday? It’s like a treasure trove, but with more glitter and less, you know, *actual* treasure." Molly scoffed, rolling her eyes. "You’re telling me you’d rather steal a bunch of plastic toys than, I don’t know, a diamond necklace or a rare painting?" Bill chuckled, pulling a tiny hammer from his pocket. "First off, diamonds are overrated. Second, have you *seen* the price tag on that LEGO set? That’s more money than my last three jobs combined. And third—" he held up a finger—"kids don’t scream when you take their toys. They just cry and say, ‘But it’s *mine*!’" Molly groaned, kicking a shoelace out of her way. "You’re insane. What if the parents show up early?" Bill winked. "Then we’re just early for dessert. Now move it—those presents aren’t gonna steal themselves." He cracked his knuckles. "And Molly? If we get caught, I’m blaming the dog."
created_at
"2026-02-20T20:17:05.661Z"
2/20/2026, 8:17:05 PM
model
"mistralai/ministral-8b-2512"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
199
moderation_latency
(null)
generation_time
2055
tokens_prompt
77
tokens_completion
362
native_tokens_prompt
69
native_tokens_completion
346
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
0.00006225
router
(null)
provider_responses
0
endpoint_id
"c85d26e1-1e0c-449b-9775-2afce7ae510b"
id
"1b938cad24754501ac4c9f8f1766c34d"
is_byok
false
latency
199
model_permaslug
"mistralai/ministral-8b-2512"
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771618625-96MrLWYGsGjVc4hYNTJJ"
upstream_id
"1b938cad24754501ac4c9f8f1766c34d"
total_cost
0.00006225
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
233
0.00%
Dialogue to Total Word Ratio
Ratio: 65.67%, Deviation: 24.33%
neededClean
false
wordsTotal
233
wordsDialogue
153
0.0004%