NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY7Z00ZJRKKX06G3FCYV1FJ
Run Details
Model:
Ministral 3 8B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
2.1s
Cost:
$0.000056
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
47.9934%
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 lights seeped through the blinds like a drunk neon saint, casting jagged shadows across the living room floor where Molly adjusted the tension on her lockpick set with the precision of a surgeon threading a needle. Bill leaned against the wall, twirling a candy cane between his fingers like a conductor’s baton, his breath fogging the air in slow, dramatic arcs. “You’re sure this isn’t just a *really* elaborate prank?” Bill asked, his voice a low murmur that might’ve been mistaken for a purring cat if anyone had been listening. Molly shot him a look that could’ve curdled milk. “No, genius. It’s a *very* well-guarded treasure trove of toys, and I *hate* toys. Especially the ones that sing.” Bill sighed, plucking a gumdrop from his pocket and popping it into his mouth. “Fine. But if we get caught, I’m blaming the piñata. That thing’s got *eyes*.” Molly smirked, already sliding a slim pick into the keyhole with the grace of a dancer. “Oh, it’s *watching* us. And it’s *laughing*.” The lock clicked open with a sound like a sigh of relief from a very relieved lock. Bill grinned. “Well, partner, looks like we’re about to make Santa’s naughty list *very* personal.”
created_at
"2026-02-20T19:20:56.62Z"
2/20/2026, 7:20:56 PM
model
"mistralai/ministral-8b-2512"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
379
moderation_latency
(null)
generation_time
1842
tokens_prompt
77
tokens_completion
323
native_tokens_prompt
69
native_tokens_completion
302
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
0.00005565
router
(null)
provider_responses
0
endpoint_id
"c85d26e1-1e0c-449b-9775-2afce7ae510b"
id
"22d5d0b3e2ed460aaf86cbe2ffbafe18"
is_byok
false
latency
379
model_permaslug
"mistralai/ministral-8b-2512"
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771615256-ZS3wMGiTsVKjBA1eBW0h"
upstream_id
"22d5d0b3e2ed460aaf86cbe2ffbafe18"
total_cost
0.00005565
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
95.99%
Matches word count
n/a
neededClean
false
words
208
0.00%
Dialogue to Total Word Ratio
Ratio: 30.29%, Deviation: 20.29%
neededClean
false
wordsTotal
208
wordsDialogue
63
47.9934%