NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHXQFC0MAGS26XNVWEVWGE9V
Run Details
Model:
Mistral Large 3
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
6.7s
Cost:
$0.000453
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9595%
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 clown car sputtered to a stop half a block from the birthday bash, its rainbow-striped bumper sagging like a deflated whoopee cushion. Molly adjusted her polka-dot bowtie in the rearview mirror, the elastic digging into her neck like a guilty conscience. "You ever notice how clown makeup smells like regret and expired cotton candy?" she muttered, peeling a fake freckle off her cheek. Bill, already halfway into his oversized diaper costume, paused mid-squat. "Only when you buy the discount brand from the back of *Circus Monthly*." He waddled toward the window, the plastic safety pins on his onesie clinking like wind chimes in a hurricane. Outside, a line of minivans idled, parents waving goodbye with the desperate enthusiasm of hostages signaling for help. Molly tossed him a sippy cup filled with lockpicks. "You take the back door. I’ll handle the piñata—it’s probably rigged with glitter bombs." Bill caught the cup, his chubby fingers struggling with the lid. "What if the kids cry?" She grinned, teeth too white against her greasepaint. "Then we tell ‘em Santa’s union went on strike. Now move—before the magician pulls a real rabbit out of his hat."
created_at
"2026-02-20T14:32:47.392Z"
2/20/2026, 2:32:47 PM
model
"mistralai/mistral-large-2512"
1/1/2512, 12:00:00 AM
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
350
moderation_latency
(null)
generation_time
6563
tokens_prompt
77
tokens_completion
305
native_tokens_prompt
69
native_tokens_completion
279
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
0.000453
router
(null)
provider_responses
0
endpoint_id
"fa718841-07ea-4b7e-b8a3-6069545c7e6a"
id
"42b8041d08124fe98a61ab1d4920724e"
is_byok
false
latency
350
model_permaslug
"mistralai/mistral-large-2512"
1/1/2512, 12:00:00 AM
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771597967-bcl2LfWIBlvJv4krEpIq"
upstream_id
"42b8041d08124fe98a61ab1d4920724e"
total_cost
0.000453
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
197
0.00%
Dialogue to Total Word Ratio
Ratio: 34.52%, Deviation: 24.52%
neededClean
false
wordsTotal
197
wordsDialogue
68
49.9595%