NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY97AX1REW0C8T2J49PZQ63
Run Details
Model:
Ministral 3 3B
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
1.8s
Cost:
$0.000053
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 500 word scene that has 30% 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 the party hall pulsed like a heartbeat, casting jagged shadows across the walls where Molly adjusted her gloves—too tight, too loud, but she’d never admit that to Bill. He was already hunched over the doorknob, his breath fogging the air like a villain in a bad action movie. “You’re gonna get us both arrested,” Bill muttered, his voice dripping with faux concern. “That security camera’s got a damn face.” Molly smirked, flipping her hair over her shoulder. “Relax, partner. We’re not here to *see* the presents. We’re here to *steal* them.” She grabbed a nearby trash can, pried open the lid with a dramatic flourish. “See? No alarms. No guards. Just a bunch of kids who’ll be too busy screaming to notice us.” Bill groaned, but then his eyes lit up. “Wait—what if we just… *swap* them? Give them a fake present, take the real ones, and vanish before anyone notices?” Molly’s grin faltered. “You’re *terrible* at this.” “No, I’m *brilliant* at this!” Bill insisted, already pulling out a small, poorly wrapped box from his pocket. “This one’s got a ‘free toy’ sticker. Perfect.” Molly snatched it back. “You’re a disaster. We’re gonna get caught.” “Nah,” Bill said, adjusting his sunglasses. “We’re gonna get rich. And then we’ll buy a *real* house. With a *real* dog.” Molly rolled her eyes but couldn’t help laughing. “Fine. But if we get caught, I’m hauling your ass to the nearest dumpster.” Bill grinned. “Deal. Now—*where* do we start?” Molly pointed to the back door, where a stack of boxes sat untouched. “There. The least likely spot.” Bill groaned. “You’re *such* a cop.” “Shut up and help,” Molly said, already pulling a lockpick from her pocket. “Or I’ll tell the cops you’re a *terrible* thief.”
created_at
"2026-02-20T19:42:58.478Z"
2/20/2026, 7:42:58 PM
model
"mistralai/ministral-3b-2512"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
209
moderation_latency
(null)
generation_time
1501
tokens_prompt
77
tokens_completion
498
native_tokens_prompt
69
native_tokens_completion
457
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
0.0000526
router
(null)
provider_responses
0
endpoint_id
"b9f6828f-aef9-498a-91f5-6816fbf72420"
id
"d1cc3b99d0fd4cb090178e029eaba00f"
is_byok
false
latency
207
model_permaslug
"mistralai/ministral-3b-2512"
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771616578-yDxztsVVunoj3zbcrNbu"
upstream_id
"d1cc3b99d0fd4cb090178e029eaba00f"
total_cost
0.0000526
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
296
0.00%
Dialogue to Total Word Ratio
Ratio: 49.32%, Deviation: 19.32%
neededClean
false
wordsTotal
296
wordsDialogue
146
0.0000%