NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY92PJGWKV1K8WMY1RC9AWE
Run Details
Model:
Ministral 3 8B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2.9s
Cost:
$0.000077
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
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 flickering "Happy Birthday!" balloon cast long shadows across the table as Molly swirled her coffee, her fingers tapping an impatient rhythm against the chipped ceramic. "Alright, Bill," she said, leaning in like she was sharing a state secret with the waiter, "we’re talking about a *children’s party*. Not some high-stakes vault. Just a bunch of kids, balloons, and enough candy to make a diabetic have a heart attack." Bill wiped his mouth with a napkin, grinning like he’d just won the lottery. "And yet, you’re the one who keeps saying we should do it. What’s the play?" "Simple. We go in, we grab the presents—*all* of them—and we’re out before the parents even realize their kids have been replaced with tiny, confused ninjas." Bill chuckled, shaking his head. "You’re insane. What if the kid’s mom recognizes you from that time you tried to sell her a ‘limited edition’ snow globe that was just a rock?" Molly rolled her eyes. "First of all, I was *very* convincing. Second, we’re not breaking in. We’re *entering as guests*." Bill froze, his coffee sloshing dangerously close to the rim. "You’re joking. You want to *socialize* with children?" "Bill, I’ve been socializing with children since I was five. I was the ringleader of the ‘Sock Thief Gang.’ We’d steal socks from the laundry line and trade them for candy. The kids *loved* me." He groaned, rubbing his temples. "And now you want to do this *on a larger scale*." Molly grinned. "Exactly. We’ll bring gifts. We’ll be *generous*. And when the parents aren’t looking, we’ll just… *borrow* the rest." Bill sighed, defeated. "You’re going to get us arrested." Molly leaned back, smug. "Nah. We’ll just blame it on the birthday boy’s *imaginary friend*."
created_at
"2026-02-20T19:40:26.588Z"
2/20/2026, 7:40:26 PM
model
"mistralai/ministral-8b-2512"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
208
moderation_latency
(null)
generation_time
2401
tokens_prompt
77
tokens_completion
474
native_tokens_prompt
69
native_tokens_completion
442
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
64
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
0.00007665
router
(null)
provider_responses
0
endpoint_id
"c85d26e1-1e0c-449b-9775-2afce7ae510b"
id
"41f6ca10c2f14eacb357f70c90e66571"
is_byok
false
latency
208
model_permaslug
"mistralai/ministral-8b-2512"
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771616426-wbNp8tkQzp4R3oXhb1NU"
upstream_id
"41f6ca10c2f14eacb357f70c90e66571"
total_cost
0.00007665
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
295
0.00%
Dialogue to Total Word Ratio
Ratio: 69.83%, Deviation: 20.17%
neededClean
false
wordsTotal
295
wordsDialogue
206
0.0000%