NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHXQKM0J1FF7JP7GDKY9AXQJ
Run Details
Model:
Mistral Small 3.2 24B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2.7s
Cost:
$0.000096
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
60.28%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
30.1376%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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 leaned against the fence of the brightly decorated backyard. "You realize this is the dumbest plan we’ve ever had, right?" Bill scratched his chin, eyeing the piñata swinging lazily in the breeze. "Dumb? No. *Brilliant.* Kids’ parties are the perfect heist. No security, just a bunch of sugar-high toddlers and distracted parents." Molly groaned. "And what’s our exit strategy? Blending in with the clowns?" "Exactly!" Bill grinned. "We dress up as the magician and his assistant. No one questions a magician. They just assume you’re doing *magic*." Molly crossed her arms. "And when the magician shows up?" Bill waved a hand. "He’s not. I canceled him. Said he had a family emergency." Molly blinked. "You *lied* to a magician?" "Technically, I lied to his booking agent. Big difference." Molly sighed. "Fine. But if we get caught, I’m blaming you. And I’m taking the blame *very* seriously." Bill clapped her on the back. "That’s the spirit! Now, let’s go steal some My Little Ponies." Molly groaned again. "I hate you." Bill grinned. "No, you don’t. You love my *genius*."
created_at
"2026-02-20T14:35:06.655Z"
2/20/2026, 2:35:06 PM
model
"mistralai/mistral-small-3.2-24b-instruct-2506"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
219
moderation_latency
(null)
generation_time
2607
tokens_prompt
77
tokens_completion
308
native_tokens_prompt
69
native_tokens_completion
297
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
0.000096
router
(null)
provider_responses
0
endpoint_id
"23fd6b91-74d8-45fc-ac00-cf141ec7f4a5"
id
"5b4a44b5c7dc411590c97921dc4a691f"
is_byok
false
latency
218
model_permaslug
"mistralai/mistral-small-3.2-24b-instruct-2506"
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771598106-4Gu5dk34NdpteCaMnPbK"
upstream_id
"5b4a44b5c7dc411590c97921dc4a691f"
total_cost
0.000096
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
60.28%
Matches word count
n/a
neededClean
false
words
185
0.00%
Dialogue to Total Word Ratio
Ratio: 70.81%, Deviation: 19.19%
neededClean
false
wordsTotal
185
wordsDialogue
131
30.1376%