NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHYAJRSYHR22VJK4C1H1D59S
Run Details
Model:
Ministral 3 8B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
2.7s
Cost:
$0.000073
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
11.37%
Dialogue to Total Word Ratio
(details)
5.6854%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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!" sign cast long shadows across the backyard as Molly adjusted the strap of her satchel, her breath fogging in the crisp evening air. "Alright, Bill," she whispered, nudging him with her elbow, "we’re about to turn this sugar rush into our own personal candy land." Bill wiped his sweaty palms on his pants, his eyes darting toward the house where laughter and the distant clink of plastic cups echoed. "Molly, I don’t know about this. What if the kid’s mom is a black belt in karate? Or worse—what if she’s got a *dog*?" Molly smirked, pulling out a pair of tiny, glittery sunglasses from her bag. "Relax, Bill. The only thing sharper than that mom’s eyes is my lockpick set. And as for the dog? We’re not stealing from the dog. We’re stealing *for* the dog. Imagine that mutt’s life—no more stolen bones, just a lifetime supply of squeaky toys." Bill groaned, rubbing his temples. "You’re evil. And also, what if the kid’s name is *Timmy*? I can’t rob a Timmy." Molly gasped, clutching her chest. "Bill, if we don’t do this, we’ll be eating cold pizza for the rest of our lives. And trust me, you’d rather have a lifetime supply of *Lego sets* than regret." She tossed him a tiny top hat. "Besides, think of the *prestige*. We’re not just thieves—we’re the *Santa Clauses of crime*." Bill sighed, adjusting the hat lopsidedly. "Fine. But if we get caught, I’m blaming you and that *glitter*." He grabbed her wrist, pulling her closer to the fence. "And Molly? If we see a single *unwrapped present*, I’m leaving you behind."
created_at
"2026-02-20T20:06:41.738Z"
2/20/2026, 8:06:41 PM
model
"mistralai/ministral-8b-2512"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
221
moderation_latency
(null)
generation_time
2097
tokens_prompt
77
tokens_completion
418
native_tokens_prompt
69
native_tokens_completion
415
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
0.0000726
router
(null)
provider_responses
0
endpoint_id
"c85d26e1-1e0c-449b-9775-2afce7ae510b"
id
"933d9a9e07894de78facc6d923756033"
is_byok
false
latency
221
model_permaslug
"mistralai/ministral-8b-2512"
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771618001-zEiMF5Vehh0eGzM7WvPz"
upstream_id
"933d9a9e07894de78facc6d923756033"
total_cost
0.0000726
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
280
11.37%
Dialogue to Total Word Ratio
Ratio: 62.14%, Deviation: 12.14%
neededClean
false
wordsTotal
280
wordsDialogue
174
5.6854%