NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY9AZFC6BEBR9W1Q43VAASC
Run Details
Model:
Ministral 3 8B
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2.0s
Cost:
$0.000062
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
2.01%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
1.0058%
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 flickering "Happy Birthday!" sign cast long shadows across the backyard as Molly adjusted the strap of her bag, her fingers twitching with anticipation. "Alright, Bill, we’re in. The cake’s got more frosting than security, and those kids are too busy opening presents to notice a ghost." Bill leaned against the fence, cracking his knuckles with a grin. "Ghost? Molly, I’m the ghost. You’re the *distraction*—remember? The one who’s supposed to make the parents think they’re losing their minds." "Oh, *please*," she scoffed, tossing a handful of glitter into the air. "I’ll be the ‘mysterious woman in a sequin cape’ who ‘accidentally’ knocks over the punch bowl. Classic move." She paused, then added, "Though if we’re being honest, I’d rather just walk in like we own the place." Bill shook his head. "And get caught? No way. We’re pros. We’ve got the *perfect* plan—steal all the presents, leave the kids with just the cake and the piñata, and vanish before the parents even realize they’ve been robbed." Molly groaned. "You’re evil. I love it." "Teamwork," Bill said, clapping her on the back. "Now, you handle the parents. I’ll handle the presents. And if anyone asks, we were *never* here." Molly grinned. "Deal. But if we get caught, I’m blaming you for not bringing enough duct tape." Bill smirked. "Worth it."
created_at
"2026-02-20T19:44:57.849Z"
2/20/2026, 7:44:57 PM
model
"mistralai/ministral-8b-2512"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
269
moderation_latency
(null)
generation_time
1689
tokens_prompt
77
tokens_completion
364
native_tokens_prompt
69
native_tokens_completion
346
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
0.00006225
router
(null)
provider_responses
0
endpoint_id
"c85d26e1-1e0c-449b-9775-2afce7ae510b"
id
"f0abb6da36bb4ec7a8e8f20b67dc1959"
is_byok
false
latency
269
model_permaslug
"mistralai/ministral-8b-2512"
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771616697-rgPDOSV2XJ63IftyOoEE"
upstream_id
"f0abb6da36bb4ec7a8e8f20b67dc1959"
total_cost
0.00006225
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
2.01%
Matches word count
n/a
neededClean
false
words
225
0.00%
Dialogue to Total Word Ratio
Ratio: 69.78%, Deviation: 20.22%
neededClean
false
wordsTotal
225
wordsDialogue
157
1.0058%