NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHYAC1RA0F8BNNX7BBXFAH3K
Run Details
Model:
Ministral 3 14B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2.6s
Cost:
$0.000074
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
51.93%
Matches word count
(details)
35.20%
Dialogue to Total Word Ratio
(details)
43.5616%
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 ski mask and leaned against the fence, watching the house glow with rainbow lights. "Alright, Bill, talk me through the plan again. I swear, if this is another one of your ‘improvised’ schemes, I’m throwing you into the kiddie pool." Bill wiped his forehead with a handkerchief. "Relax, Mol. We’re not exactly *breaking in*—we’re *crashing*. Classic distraction heist. You play the overenthusiastic mom, I’ll be the ‘lost’ dad, and we waltz right in like we belong." "Oh, *wonderful*. So I’m supposed to charm a room full of screaming toddlers while you ‘accidentally’ knock over a piñata and make a run for it?" "Hey, the piñata’s full of candy. That’s *our* cut." Molly groaned. "You realize the presents are under the tree, not in the piñata, right?" "Details, Mol. We’ll cross that bridge when we’re knee-deep in wrapped toys." A child’s laughter echoed from the house. Molly sighed. "Fine. But if I get finger-painted by a three-year-old, I’m blaming you." Bill grinned. "Deal. Now, remember—smile, act natural, and if anyone asks, we’re *definitely* here for the cupcakes."
created_at
"2026-02-20T20:03:01.527Z"
2/20/2026, 8:03:01 PM
model
"mistralai/ministral-14b-2512"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
237
moderation_latency
(null)
generation_time
2251
tokens_prompt
77
tokens_completion
304
native_tokens_prompt
69
native_tokens_completion
301
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
64
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
0.000074
router
(null)
provider_responses
0
endpoint_id
"0b53717b-9af5-4de3-80af-ebedd2adf981"
id
"4649f7e4ea4a43c6ad2e6899cb18861d"
is_byok
false
latency
237
model_permaslug
"mistralai/ministral-14b-2512"
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771617781-pvKi6vnUc5lllm56zqQX"
upstream_id
"4649f7e4ea4a43c6ad2e6899cb18861d"
total_cost
0.000074
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
51.93%
Matches word count
n/a
neededClean
false
words
184
35.20%
Dialogue to Total Word Ratio
Ratio: 79.89%, Deviation: 10.11%
neededClean
false
wordsTotal
184
wordsDialogue
147
43.5616%