NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHYAE1B94WCWJY1M4D73W4R0
Run Details
Model:
Ministral 3 8B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2.4s
Cost:
$0.000072
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
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
The neon glow of a neon sign flickered outside the diner window, casting long shadows over the sticky booth where Molly leaned back, twirling a straw through her iced coffee like it was a magic wand. Bill slid into the seat across from her, already unbuttoning his jacket to reveal a suspiciously shiny new watch—one he’d "borrowed" from a very confused accountant. "Alright, Molly," Bill said, adjusting his cuffs with a flourish. "We’re stealing a *children’s party*. What’s the play?" Molly took a slow sip, then set the glass down with a dramatic sigh. "First off, Bill, you’re wearing *that* watch. Kids will see it and think it’s a clue. Second—" she tapped her temple, "—we’re not stealing *from* the kids. We’re stealing *for* the kids. Ever think about how many toys end up in landfills because some trust-fund brat outgrows them in a week?" Bill blinked. "That’s… actually a good point." "Good. So here’s the plan: we crash the party as ‘aunt and uncle’—you’re the loud, obnoxious one, I’m the ‘sweet but slightly unhinged’ one. We ‘accidentally’ knock over the gift table, then ‘help’ the kids pick out their presents while we ‘accidentally’ pocket the rest. Bonus points if we can swap out a few ‘expensive’ toys for knockoffs we’ve been sitting on." Bill grinned. "You’re evil." "Efficiency, Bill. Pure efficiency." She leaned in. "And if anyone asks, we’re here to ‘rescue’ the kids from their *terrible* parents. Works every time." Bill raised his coffee cup. "To chaos and candy canes." Molly clinked hers against it. "To the greatest heist of all time."
created_at
"2026-02-20T20:04:06.654Z"
2/20/2026, 8:04:06 PM
model
"mistralai/ministral-8b-2512"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
94
moderation_latency
(null)
generation_time
1685
tokens_prompt
77
tokens_completion
432
native_tokens_prompt
69
native_tokens_completion
408
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
0.00007155
router
(null)
provider_responses
0
endpoint_id
"c85d26e1-1e0c-449b-9775-2afce7ae510b"
id
"e18c07bd2bb64e6f8ffa841f16d76adb"
is_byok
false
latency
94
model_permaslug
"mistralai/ministral-8b-2512"
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771617846-fTG2kw4PsE1Fjnbr1g6R"
upstream_id
"e18c07bd2bb64e6f8ffa841f16d76adb"
total_cost
0.00007155
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
267
0.00%
Dialogue to Total Word Ratio
Ratio: 49.06%, Deviation: 40.94%
neededClean
false
wordsTotal
267
wordsDialogue
131
0.0000%