NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHXQ0GWARRDV1958NYF71FCV
Run Details
Model:
Mistral Small 3.2 24B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
4.6s
Cost:
$0.000109
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
2.01%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
1.0058%
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
Molly adjusted her oversized sunglasses and nudged Bill with her elbow. "You sure this is the right house? It looks like a rainbow exploded on a cupcake." Bill squinted at the inflatable unicorn bouncing in the front yard. "Positive. The kid’s parents are loaded. Presents will be top-tier." Molly pulled a clipboard from her bag, scanning the notes. "According to my intel, the birthday girl’s favorite color is ‘sparkle.’ Whatever that means." Bill scratched his head. "We’re stealing from a five-year-old. This is either genius or a new low." Molly grinned. "Both. Now, the party starts in twenty. We’ve got exactly twelve minutes to case the joint before the clown arrives." Bill groaned. "Clowns? You didn’t mention clowns." "Relax. We’ll blend in. You’re wearing a Hawaiian shirt. You already look like a deranged uncle." Bill tugged at his collar. "This was your idea. I look ridiculous." Molly patted his shoulder. "Focus. We need a distraction. Something loud, something chaotic." Bill’s eyes lit up. "I’ve got it. You remember that time we set off fireworks in the bakery?" Molly sighed. "That ended with a cake fight. And a restraining order." "Details. This’ll be different. Trust me." Molly groaned. "Fine. But if we get arrested, I’m telling them you’re my kid." Bill gasped. "I’m only thirty-two!" Molly shrugged. "You dress like a grandpa."
created_at
"2026-02-20T14:24:40.853Z"
2/20/2026, 2:24:40 PM
model
"mistralai/mistral-small-3.2-24b-instruct-2506"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
236
moderation_latency
(null)
generation_time
4294
tokens_prompt
77
tokens_completion
375
native_tokens_prompt
69
native_tokens_completion
339
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
0.0001086
router
(null)
provider_responses
0
endpoint_id
"23fd6b91-74d8-45fc-ac00-cf141ec7f4a5"
id
"3811255ec503426db897320ad7f5a330"
is_byok
false
latency
228
model_permaslug
"mistralai/mistral-small-3.2-24b-instruct-2506"
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771597480-CCVIzL4q4yDA7NPh4MCT"
upstream_id
"3811255ec503426db897320ad7f5a330"
total_cost
0.0001086
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
2.01%
Matches word count
n/a
neededClean
false
words
225
0.00%
Dialogue to Total Word Ratio
Ratio: 72.89%, Deviation: 62.89%
neededClean
false
wordsTotal
225
wordsDialogue
164
1.0058%