NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM09VWA3JP26NS17M25VHSBT
Run Details
Model:
Mistral Small 4
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3.0s
Cost:
$0.000190
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
3.30%
Dialogue to Total Word Ratio
(details)
51.3394%
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 hat, crouching behind a bush outside the party venue. "You sure the presents aren’t locked up?" Bill wiped his forehead with a napkin. "According to the rental company, they just stack ‘em by the door like little trophies for us to take." Molly smirked. "So we’re just stealing from kids." "Stealing from a corporation renting out party goods. They’re not even the toy manufacturers." "Sure, and Santa’s workshop isn’t a sweat shop, either." Molly rolled her eyes. "Fine, but we grab the big stuff first—easier to resell." Bill nodded. "Got it. But if I see a piñata, I’m taking that too. Who doesn’t love a good piñata?" Molly groaned. "That’s just filled with candy." "And therefore, even more valuable." She sighed. "We’re monsters." Bill grinned. "Nah, we’re professionals. Now shut up, we’ve got 45 minutes till the parents start arriving." Molly peeked around the bush. "You sure no one’s checking the presents?" "Yeah, ‘cause they’re too busy serving juice in plastic cups to care about a pile of wrapped junk." Bill checked his watch. "Time to move." Molly grabbed her bag. "Last rule—if we see a clown, we bail." "Deal."
created_at
"2026-03-18T11:04:04.177Z"
3/18/2026, 11:04:04 AM
model
"mistralai/mistral-small-2603"
1/1/2603, 12:00:00 AM
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
367
moderation_latency
(null)
generation_time
2954
tokens_prompt
77
tokens_completion
324
native_tokens_prompt
81
native_tokens_completion
297
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
0.00019035
router
(null)
provider_responses
0
endpoint_id
"f5ed6283-4e17-457d-98cd-2ec0c318171d"
id
"ee800ab904f741b593644972d57fb256"
is_byok
false
latency
367
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-1773831844-Mz1prmrYJgsMylDTaQ7o"
upstream_id
"ee800ab904f741b593644972d57fb256"
total_cost
0.00019035
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
99.38%
Matches word count
n/a
neededClean
false
words
195
3.30%
Dialogue to Total Word Ratio
Ratio: 76.41%, Deviation: 13.59%
neededClean
false
wordsTotal
195
wordsDialogue
149
51.3394%