NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM09PQYT6XM9NSXBDGGAEX2V
Run Details
Model:
Mistral Small 4
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
3.8s
Cost:
$0.000212
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
9.61%
Matches word count
(details)
99.97%
Dialogue to Total Word Ratio
(details)
54.7880%
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 rain drummed steadily against the parked van as Molly and Bill huddled over a crinkled party invitation in the dim glow of a flashlight. The Bouquet Children’s Extravaganza was tonight, and the invite promised bouncy castles, costumed caricatures, and, most importantly, a treasure trove of unwrapped loot just waiting for the taking. Bill adjusted his acrobat beard, his eyes glinting with mischief. "You sure about this one? Cops’ll be crawling around like ants on a dropped ice cream cone." Molly stuffed the invitation into her pocket, her smirk sharp under the streetlamp’s flicker. "Relax. Adults think kids just bash the presents open. Half those boxes are still in pristine condition. Perfect for the black market, no questions asked." Bill scratched his cheek beneath his fake mustache, wincing as the glue tugged. "Right. Steal from children. How noble." "Nothing noble about it," Molly said, snapping her gloves. "It’s about supply and demand. Ever try reselling a half-deflated Whoopee cushion on eBay? No takers." Bill groaned, slumping against the van seat. "We’re monsters." "Look, we take the good stuff—video game consoles, remote-control cars—and leave the glitter pens and Barbie outfits. Minimal trauma." Bill muttered, "You mean maximum profit." She grinned, tossing him a tiny lockpick set from her pocket. "Now hurry up and pick the lock before the clowns start dancing."
created_at
"2026-03-18T11:01:15.88Z"
3/18/2026, 11:01:15 AM
model
"mistralai/mistral-small-2603"
1/1/2603, 12:00:00 AM
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
382
moderation_latency
(null)
generation_time
3759
tokens_prompt
77
tokens_completion
369
native_tokens_prompt
81
native_tokens_completion
333
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
0.00021195
router
(null)
provider_responses
0
endpoint_id
"f5ed6283-4e17-457d-98cd-2ec0c318171d"
id
"f4e0af276d0a45e3af0ac91568f20bb4"
is_byok
false
latency
382
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-1773831675-S8WiQ0veNK60kqe6MFT6"
upstream_id
"f4e0af276d0a45e3af0ac91568f20bb4"
total_cost
0.00021195
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
9.61%
Matches word count
n/a
neededClean
false
words
222
99.97%
Dialogue to Total Word Ratio
Ratio: 48.66%, Deviation: 1.34%
neededClean
false
wordsTotal
224
wordsDialogue
109
54.7880%