NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHXPW76E0CFDCTN4XW4T8J7V
Run Details
Model:
Mistral Large 3
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
6.8s
Cost:
$0.000517
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
97.9931%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 the glittery unicorn horn strapped to her head and squinted at the inflatable bounce castle. "You’re sure this is the plan? We’re robbing a *kids’ party*?" Bill, already halfway into a rainbow-striped onesie, shot her a look. "It’s genius. No security, no alarms, just a bunch of distracted parents and sugar-high toddlers. We waltz in, grab the loot, and waltz out before anyone notices." Molly plucked a juice box from a nearby table and took a sip. "I dunno, Bill. This feels… wrong. Like, morally *and* logistically. What if some kid starts crying?" "Then we tell them we’re the *present fairies*." He wiggled his fingers for emphasis. "Kids love fairies." She tossed the empty juice box into a trash can. "And what if the parents *don’t* love fairies?" Bill grinned, pulling a glitter cannon from his backpack. "Then we hit ‘em with the old *distraction and dash*." He aimed it at the ceiling. "Three… two…" Molly lunged for the cannon. "Don’t you *dare*—" A burst of pink sparkles exploded overhead, raining down on a table of cupcakes. A chorus of delighted shrieks erupted from the kids. Bill clapped his hands. "See? *Teamwork.* Now grab a sack and let’s move before the sugar crash hits."
created_at
"2026-02-20T14:22:19.865Z"
2/20/2026, 2:22:19 PM
model
"mistralai/mistral-large-2512"
1/1/2512, 12:00:00 AM
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
357
moderation_latency
(null)
generation_time
6756
tokens_prompt
77
tokens_completion
327
native_tokens_prompt
69
native_tokens_completion
322
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
0.0005175
router
(null)
provider_responses
0
endpoint_id
"fa718841-07ea-4b7e-b8a3-6069545c7e6a"
id
"d571b358749844c1baf8e686a32fad5e"
is_byok
false
latency
356
model_permaslug
"mistralai/mistral-large-2512"
1/1/2512, 12:00:00 AM
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771597339-lmdPfgdgOnocIbCuJYdX"
upstream_id
"d571b358749844c1baf8e686a32fad5e"
total_cost
0.0005175
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
95.99%
Matches word count
n/a
neededClean
false
words
208
100.00%
Dialogue to Total Word Ratio
Ratio: 49.52%, Deviation: 0.48%
neededClean
false
wordsTotal
208
wordsDialogue
103
97.9931%