NC Bench
Overview
About
Tests
Models
Model
Mistral Small Creative
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2026-02-08-01KGYX4F3R4VF3PT53NMZJ2E87
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 glittery party hat and leaned against the bakery’s display case, eyeing the inflatable castle across the street. "Alright, Bill, we’ve got a problem. The kid’s birthday party is *inside* the castle. How do we hit a target that’s literally a bouncy fortress?" Bill wiped frosting off his sleeve—he’d been sampling the cupcakes "for research." "Easy. We go in as clowns. No one questions clowns at a kids’ party. We’re basically invisible." "Clowns? Bill, the last time you wore face paint, you scared a toddler into next week. The kid’s still in therapy." "Details. Besides, we’ll be *fun* clowns. I’ll juggle. You’ll do… whatever it is you do." "I *do* not do anything. That’s the problem. I’m not a performer, I’m a thief. My skills are picking locks and not getting caught, not honking my nose for applause." Bill grabbed a balloon animal from the counter and twisted it into a sad-looking dog. "Then be the *quiet* clown. The mysterious one. Kids love that. You’ll be the deep, brooding clown who hands out presents instead of stealing them." Molly snatched the balloon dog and deflated it with a sharp *pop*. "No. We’re going in as *parents*. Rich, distracted parents who ‘forgot’ their kid’s gift and need to ‘borrow’ a few from the pile." Bill groaned. "Molly, we don’t *look* like parents. You’ve got a tattoo of a dagger on your neck, and I still have last week’s prison orange in my go-bag." "Exactly. We’ll be *cool* parents. The kind who let their kids eat cake for dinner and don’t ask where the presents went. Trust me, no one questions the chaotic ones." She adjusted her hat again. "Now, how do we get past the piñata?"
created_at
"2026-02-08T15:15:17.238058+00:00"
Sunday, February 8th, 2026 at 3:15:17 PM GMT+00:00
model
"mistralai/mistral-small-creative-20251216"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
223
moderation_latency
(null)
generation_time
1991
tokens_prompt
61
tokens_completion
413
native_tokens_prompt
69
native_tokens_completion
426
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
0.0001347
router
(null)
provider_responses
0
id
"86e35d74c5af4ef3bf25abd964799298"
status
200
is_byok
false
latency
223
endpoint_id
"0118a65e-79f9-48b0-924e-38c4a41378e1"
provider_name
"Mistral"
model_permaslug
"mistralai/mistral-small-creative-20251216"
api_type
"completions"
id
"gen-1770563714-LdbU0AbbvV3GoBpHATzy"
upstream_id
"86e35d74c5af4ef3bf25abd964799298"
total_cost
0.0001347
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
290
7.0665%
Dialogue to Total Word Ratio
Ratio: 77.24%, Deviation: 12.76%
neededClean
false
wordsTotal
290
wordsDialogue
224
3.5332%