NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHXPBCEXTFXB1CX0M7VH0W92
Run Details
Model:
Mistral Large 3
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
8.3s
Cost:
$0.000548
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
0.49%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.2460%
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 glittery unicorn horn headband and squinted at the balloon arch sagging over the backyard gate. "You’re sure this is the right place? Because I’m pretty sure we just walked into a toddler’s fever dream." Bill scratched his chin, where a temporary tattoo of a dinosaur was peeling off. "Positive. Intel says the birthday kid’s dad is some tech bro who ‘forgot’ to pay his taxes. Presents are just sitting there, unguarded, like a buffet of guilt gifts." Molly eyed a piñata shaped like a rainbow narwhal. "We’re robbing a *children’s party*. This is the lowest we’ve ever sunk." "Low? Molly, we’re *elevated*. Think about it—no alarms, no guards, just a bunch of distracted parents Instagramming their kids’ cupcake faces. It’s the perfect crime." "Except for the part where we’re dressed like we escaped from a My Little Pony convention." Bill waved a hand. "Details. We blend in. Besides, if anyone asks, we’re the *cool* aunt and uncle. The ones who show up with extra juice boxes and zero life skills." Molly sighed, plucking a rogue glitter bomb off her sleeve. "Fine. But if I get glitter in my hair, I’m taking it out of your cut." "Deal. Now, let’s case the joint—discreetly." Bill grabbed a handful of party favors from a table. "Ooh, mini slime kits. Jackpot." Molly groaned. "We’re the worst."
created_at
"2026-02-20T14:13:08.368Z"
2/20/2026, 2:13:08 PM
model
"mistralai/mistral-large-2512"
1/1/2512, 12:00:00 AM
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
340
moderation_latency
(null)
generation_time
7974
tokens_prompt
77
tokens_completion
360
native_tokens_prompt
69
native_tokens_completion
342
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
0.0005475
router
(null)
provider_responses
0
endpoint_id
"fa718841-07ea-4b7e-b8a3-6069545c7e6a"
id
"6aa6d1fe25c746519fb4c9ff7ba3662d"
is_byok
false
latency
340
model_permaslug
"mistralai/mistral-large-2512"
1/1/2512, 12:00:00 AM
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771596788-vR5mahjldXRZwZ2DaZ42"
upstream_id
"6aa6d1fe25c746519fb4c9ff7ba3662d"
total_cost
0.0005475
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
0.49%
Matches word count
n/a
neededClean
false
words
227
0.00%
Dialogue to Total Word Ratio
Ratio: 70.48%, Deviation: 19.52%
neededClean
false
wordsTotal
227
wordsDialogue
160
0.2460%