NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM07GZDXFZJ3287CATA1NPCN
Run Details
Model:
Mistral Small 4
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3.4s
Cost:
$0.000202
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
27.17%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
13.5829%
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 rain drummed on the stolen ice-cream van, turning the tarp into a bass drum. Molly wiped mascara smear from her cheek with the back of her glove, leaving a streak like a sad clown. "You sure the party’s still on? Weather’s got to cancel ch—" "Bill, shut up." Molly adjusted her elf ears. "They’re not canceling. No parent cancels two hours of free pizza and piñatas for little Timmy’s birthday. That’s a crime against childhood." "Fine, but low altitude." Bill tapped the van’s hood. "No sense climbing over bouncy castles if we can roll right through em." Molly squinted at the house—twinkling lights, a floodlit bouncy castle flapping like a dying inflatable whale. "Van won’t fit through that gate. Worse, the driveway’s got those little solar path lights. Trip one, and every demon-child within earshot yells that someone broke in." Bill scratched his fake beard. "So we park on Maple, cut through the back fence, snag the pile under the slide before the dad starts grilling." Molly nodded. "Side entrance, under the cover of the karaoke machine. Big gift pile’s by the punch bowl; easy lift." Bill grinned. "We’ll be out before the cake’s even cut." Molly grabbed the lock picks. "Only thing sweeter than Timmy’s presents? Doing it while he sings ‘Baby Shark’ at full volume."
created_at
"2026-03-18T10:23:09.773Z"
3/18/2026, 10:23:09 AM
model
"mistralai/mistral-small-2603"
1/1/2603, 12:00:00 AM
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
332
moderation_latency
(null)
generation_time
3222
tokens_prompt
77
tokens_completion
350
native_tokens_prompt
81
native_tokens_completion
317
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
0.00020235
router
(null)
provider_responses
0
endpoint_id
"f5ed6283-4e17-457d-98cd-2ec0c318171d"
id
"24cdc1ff1d814437b016cd65a7cca542"
is_byok
false
latency
332
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-1773829389-awm4wxGZycI5d1e2dCF9"
upstream_id
"24cdc1ff1d814437b016cd65a7cca542"
total_cost
0.00020235
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
27.17%
Matches word count
n/a
neededClean
false
words
219
0.00%
Dialogue to Total Word Ratio
Ratio: 65.16%, Deviation: 24.84%
neededClean
false
wordsTotal
221
wordsDialogue
144
13.5829%