NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY922WX62CVM3FGJ43PEG7H
Run Details
Model:
Ministral 3 14B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
2.5s
Cost:
$0.000082
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
99.55%
Dialogue to Total Word Ratio
(details)
49.7782%
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
The warehouse smelled like stale popcorn and regret, the kind of regret that comes from realizing you’ve just agreed to rob a children’s party. Molly adjusted her ski mask, the elastic digging into her forehead like a guilty conscience. Bill fidgeted with a lockpick, his breath fogging up the dim light. “You sure about this?” Molly whispered, eyeing the blue balloon tied to the doorknob of their target—a suburban McMansion where some kid’s fifth birthday was currently being ruined by the presence of *gifts*. “Last time we hit a party, we got chased by a guy in a superhero cape.” Bill didn’t look up. “That was a *bachelorette*. This is *kids*. They’ll just cry and eat cake.” “And the parents?” “Distracted. One’s filming the whole thing for TikTok, the other’s passed out in the hot tub.” Molly crossed her arms. “You checked?” “Cross my heart.” Bill held up a finger, then immediately dropped it. “Also, the security system’s a motion-activated *piñata*. We smash it, we get candy.” Molly groaned. “We’re stealing *toys* from *children*.” “Think of it as redistributing wealth,” Bill said, finally popping the lock. “The rich kid gets one less Lego set. Some poor kid gets *two*.” Molly sighed, stepping over the threshold. “If we get caught, I’m telling everyone you cried during *The Lion King*.” Bill grinned, already stuffing a stuffed animal into his bag. “Worth it.”
created_at
"2026-02-20T19:40:06.443Z"
2/20/2026, 7:40:06 PM
model
"mistralai/ministral-14b-2512"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
212
moderation_latency
(null)
generation_time
2125
tokens_prompt
77
tokens_completion
392
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
0.0000822
router
(null)
provider_responses
0
endpoint_id
"0b53717b-9af5-4de3-80af-ebedd2adf981"
id
"b7752ca8dde14f9ba0e497508e440562"
is_byok
false
latency
212
model_permaslug
"mistralai/ministral-14b-2512"
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771616406-pbjdWzURnxODBGGBC9vu"
upstream_id
"b7752ca8dde14f9ba0e497508e440562"
total_cost
0.0000822
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
232
99.55%
Dialogue to Total Word Ratio
Ratio: 47.41%, Deviation: 2.59%
neededClean
false
wordsTotal
232
wordsDialogue
110
49.7782%