NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHXPF0E0P5R1D8NFTCS1QKVK
Run Details
Model:
Mistral Small 3.2 24B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
4.8s
Cost:
$0.000090
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.6885%
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 rain drummed against the roof of the stolen ice cream truck as Molly adjusted her oversized sunglasses and frowned at the blueprints spread across the dashboard. Bill, chewing on a stolen candy cane, leaned over her shoulder, his breath minty and slightly panicked. “You sure this is the right plan?” he asked, voice muffled by the candy. Molly tapped the blueprints. “Positive. The party’s in full swing, the parents are distracted, and the presents are piled high. It’s like Christmas came early for us.” Bill swallowed the candy cane. “But it’s a *children’s* party. What if they cry?” Molly smirked. “Then we’ll cry too. Emotional support thieves, that’s us.” Outside, the sound of laughter and a piñata being bashed echoed through the open window. Bill wiped his palms on his pants. “What if the clown sees us?” Molly grabbed a whoopee cushion from the glove compartment. “Then we’ll distract him with this. Trust me, no one can resist a whoopee cushion.” Bill sighed. “You’re insane.” Molly grinned. “And you love it.” They slipped out of the truck, the whoopee cushion tucked under Molly’s arm, ready to infiltrate the most chaotic heist of their careers.
created_at
"2026-02-20T14:15:06.955Z"
2/20/2026, 2:15:06 PM
model
"mistralai/mistral-small-3.2-24b-instruct-2506"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
325
moderation_latency
(null)
generation_time
4407
tokens_prompt
77
tokens_completion
327
native_tokens_prompt
69
native_tokens_completion
278
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
0.0000903
router
(null)
provider_responses
0
endpoint_id
"23fd6b91-74d8-45fc-ac00-cf141ec7f4a5"
id
"54b6292cbd0042f09a46ca3eb7d0ded3"
is_byok
false
latency
325
model_permaslug
"mistralai/mistral-small-3.2-24b-instruct-2506"
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771596906-S6Lcx1pZSEhSwpkptIfZ"
upstream_id
"54b6292cbd0042f09a46ca3eb7d0ded3"
total_cost
0.0000903
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
99.38%
Matches word count
n/a
neededClean
false
words
195
0.00%
Dialogue to Total Word Ratio
Ratio: 38.46%, Deviation: 28.46%
neededClean
false
wordsTotal
195
wordsDialogue
75
49.6885%