NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM08KH7RGBSTV7WXB3G3JFZ9
Run Details
Model:
Mistral Small 4
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
3.8s
Cost:
$0.000217
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0004%
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 wiped grease from her hands with a rag that may once have been white. "Alright, Bill, we’ve scoped the place. A hundred kids, balloons, clown, the works. Security? One sleepy guy in a vest who’s more interested in his cheese puffs than the glowing exit signs." Bill adjusted his fake mustache, the one with the tiny cactus glued to it. "And the presents?" "Stacked by the door like a buffet. Action figures, tablets, whatever ‘Roblox’ is." Molly grinned. "We hit when the clown does his balloon animals. Chaos is our best friend. Grab and go." Bill nodded, then winced as the cactus mustache tickled his nose. "What’s the clown’s routine? I need specifics." "Thirty seconds for a giraffe, forty for a sword—oh, and he’s lactose intolerant so he’s got a backup cocoa cart with coconut milk." Molly pulled out a floor plan. "We go in through the kitchen, out through the gift zone, meet back at the van. Easy." Bill squinted at the plan. "The van’s a minivan full of stolen jelly shoes. We’ll stick out like—" "Like we belong," Molly cut in. "Parents assume anyone in a minivan is just ferrying more joy. Plus we can hide presents under the seats." Bill sighed. "We’re stealing from kids." Molly tossed him a pair of kid-sized sunglasses. "Bill, we’re leveling up the game. This isn’t stealing. It’s redistributing joy with extreme prejudice."
created_at
"2026-03-18T10:42:02.119Z"
3/18/2026, 10:42:02 AM
model
"mistralai/mistral-small-2603"
1/1/2603, 12:00:00 AM
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
390
moderation_latency
(null)
generation_time
3734
tokens_prompt
77
tokens_completion
363
native_tokens_prompt
81
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
0.00021735
router
(null)
provider_responses
0
endpoint_id
"f5ed6283-4e17-457d-98cd-2ec0c318171d"
id
"27de72df07a84cca9225bd4a31a88e0f"
is_byok
false
latency
390
model_permaslug
"mistralai/mistral-small-2603"
1/1/2603, 12:00:00 AM
provider_name
"Mistral"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1773830522-M8PWXyFNDm9afX6bD5mv"
upstream_id
"27de72df07a84cca9225bd4a31a88e0f"
total_cost
0.00021735
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
233
0.00%
Dialogue to Total Word Ratio
Ratio: 71.37%, Deviation: 21.37%
neededClean
false
wordsTotal
234
wordsDialogue
167
0.0004%