NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0A218KS94EP32004S6KP6E
Run Details
Model:
Mistral Small 4
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
3.6s
Cost:
$0.000199
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
0.21%
Matches word count
(details)
94.90%
Dialogue to Total Word Ratio
(details)
47.5583%
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 warehouse loomed under the pale moon, its windows fogged with the ghostly glow of discarded birthday decorations. Molly adjusted her neon pink ski mask and sighed, peering at the security panel like it was a calculus exam she hadn’t studied for. "Third panel from the left," she muttered, tapping the lock sequence into her wrist-mounted decoder with the precision of a cat poking a digital alarm with its tail. Beside her, Bill knelt in his oversized hoodie, fingers dancing over a map that smelled faintly of old nachos. "You sure this'll work?" he whispered, voice cracking just enough to betray his nerves. The presents inside were worth more than their last three jobs combined—or at least, that’s what the spreadsheet on his phone insisted. Molly shot him a look. "Relax. We’re not defusing a nuke. It’s a *Nerf blaster* cannonade in there. Who installs motion sensors for a bunch of toddlers?" Bill didn’t answer. His eyes were locked on the distant flicker of party lights, imagining the haul: a robotic dinosaur, a tower of gift cards, maybe even a cake shaped like a dragon. He swallowed hard. "Right. Let’s move." Molly slinked toward the loading dock, her lockpicks glinting under the floodlights. Behind them, a single helium balloon, half-deflated, groaned in the wind, as if it had seen this before and knew how it would end.
created_at
"2026-03-18T11:07:25.855Z"
3/18/2026, 11:07:25 AM
model
"mistralai/mistral-small-2603"
1/1/2603, 12:00:00 AM
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
344
moderation_latency
(null)
generation_time
3551
tokens_prompt
77
tokens_completion
350
native_tokens_prompt
81
native_tokens_completion
311
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
0.00019875
router
(null)
provider_responses
0
endpoint_id
"f5ed6283-4e17-457d-98cd-2ec0c318171d"
id
"83831f8528bc4d39aba57ab70bfe2d73"
is_byok
false
latency
344
model_permaslug
"mistralai/mistral-small-2603"
1/1/2603, 12:00:00 AM
provider_name
"Mistral"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1773832045-IP6ZKRyzgOYNfnncBu6I"
upstream_id
"83831f8528bc4d39aba57ab70bfe2d73"
total_cost
0.00019875
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
0.21%
Matches word count
n/a
neededClean
false
words
228
94.90%
Dialogue to Total Word Ratio
Ratio: 14.78%, Deviation: 4.78%
neededClean
false
wordsTotal
230
wordsDialogue
34
47.5583%