NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY94E2AJDGQX4RKQP6X69BX
Run Details
Model:
Ministral 3 14B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
3.0s
Cost:
$0.000083
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
0.08%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0424%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 store’s window cast jagged shadows across the alley as Molly adjusted her ski mask, the elastic biting into her forehead like a disapproving parent. Bill crouched beside her, fingers twitching over the lockpick set in his pocket, his breath fogging in the cold air. They’d scoped the place for three days—easy in, easy out, or so the recon suggested. The only problem was the *kids*. “You sure about this?” Molly whispered, though the question was more for the universe than Bill. “Last time we hit a birthday party, we got chased by a six-year-old with a sparkler.” Bill didn’t look up from the lock. “That was one time. And he tripped.” A giggle drifted from inside, followed by the unmistakable sound of wrapping paper being torn. Molly’s stomach growled—traitor. She’d had a protein bar at noon. “We’re not monsters. We’re just… redistributing wealth.” Bill finally glanced at her, his eyes gleaming behind the mask. “Wealth? Molly, these are *gifts*. A Lego set, a dollhouse, a—” He paused, listening. “—a *fidget spinner*.” She groaned. “Ugh, why’d they even put that in there? It’s not even a real toy.” Bill grinned. “Because some kid’s mom thought it was ‘calming.’” He wiggled the lockpick. “Five minutes. In and out. Unless we get ambushed by the clown.” Molly sighed. “There’s no clown.” “Yet.”
created_at
"2026-02-20T19:41:23.413Z"
2/20/2026, 7:41:23 PM
model
"mistralai/ministral-14b-2512"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
225
moderation_latency
(null)
generation_time
2668
tokens_prompt
77
tokens_completion
378
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
0.000083
router
(null)
provider_responses
0
endpoint_id
"0b53717b-9af5-4de3-80af-ebedd2adf981"
id
"7720a1921f3c43f792b8c188d7b12701"
is_byok
false
latency
225
model_permaslug
"mistralai/ministral-14b-2512"
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771616483-fl4CkCSJ5t90kp4WYilP"
upstream_id
"7720a1921f3c43f792b8c188d7b12701"
total_cost
0.000083
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
0.08%
Matches word count
n/a
neededClean
false
words
229
0.00%
Dialogue to Total Word Ratio
Ratio: 38.43%, Deviation: 28.43%
neededClean
false
wordsTotal
229
wordsDialogue
88
0.0424%