NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHXPXZ0F1S4FS7D0040KTY1B
Run Details
Model:
Mistral Large 3
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
7.7s
Cost:
$0.000588
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
44.25%
Dialogue to Total Word Ratio
(details)
22.1271%
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 swaying in the breeze. "You’re sure this is the plan? We’re not just crashing a kid’s birthday for the free cake?" Bill, already halfway into a rainbow-striped onesie, shot her a look. "The cake’s a bonus. But the loot—Molly, the *loot*—is in those presents. Did you see the wish list? That kid asked for a *pony*." "Yeah, and a PlayStation, a drone, and a lifetime supply of gummy worms. Which, by the way, is the only thing on that list we’re actually qualified to steal." Bill zipped up his onesie with a flourish. "Details. We’re not here for the *practical* gifts. We’re here for the *expensive* ones. The ones that make parents cry when they see the price tag." Molly sighed, adjusting her fake freckles. "Fine. But if we get caught, I’m telling them you made me wear this." "Please. You *love* the horn. You’ve been practicing your ‘magical unicorn giggle’ all morning." "It’s *versatile*. Also, if we have to run, I can use it to distract security." Bill grinned. "See? You’re a natural. Now, phase one: infiltrate the party. Phase two: locate the presents. Phase three—" "Phase three: don’t get glitter bombed by a six-year-old." "Too late. I already got glitter bombed by *you* when you put on that horn." Molly gasped. "That was an *accident*." "Sure it was. Just like this heist."
created_at
"2026-02-20T14:23:17.019Z"
2/20/2026, 2:23:17 PM
model
"mistralai/mistral-large-2512"
1/1/2512, 12:00:00 AM
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
336
moderation_latency
(null)
generation_time
7610
tokens_prompt
77
tokens_completion
376
native_tokens_prompt
69
native_tokens_completion
369
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
0.000588
router
(null)
provider_responses
0
endpoint_id
"fa718841-07ea-4b7e-b8a3-6069545c7e6a"
id
"228406111c5e4d08853c2c21b51e47e7"
is_byok
false
latency
336
model_permaslug
"mistralai/mistral-large-2512"
1/1/2512, 12:00:00 AM
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771597397-25pUOQNLQttftCvtc9wi"
upstream_id
"228406111c5e4d08853c2c21b51e47e7"
total_cost
0.000588
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
241
44.25%
Dialogue to Total Word Ratio
Ratio: 80.50%, Deviation: 9.50%
neededClean
false
wordsTotal
241
wordsDialogue
194
22.1271%