NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM07KRWEE359KEYD77Y4Z08N
Run Details
Model:
Mistral Small 4 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
11.9s
Cost:
$0.000985
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.8722%
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 tapped her fingers on the diner table, her mind already three steps ahead. "The Johnson kid’s party. Community center. We go in when they’re cutting the cake." Bill slurped his coffee, grimacing at the taste. "Cake? That’s your big plan?" "Sure is." Molly’s grin was razor sharp. "Every kid in there’s gonna be too sugared up to notice us swiping their loot." Bill raised an eyebrow. "And how do we not get caught in the chaos?" She slid a napkin across with a crude map. "Rear door’s unlocked. Presents under that sad little tree. I take ‘em, you stand guard dressed as... a pirate." "A pirate?" Bill nearly choked. "Why a pirate?" "Because clowns are scary. Pirates are fun." She winked. "Sword fights in the craft corner—who’s gonna notice a guy in an eye patch amidst all the chaos?" Bill rubbed his temples. "I hate my life." Molly leaned in, voice dripping with false sympathy. "Come on, Bill. For the presents. All those colorful, plastic, *stealable* presents." Bill groaned. "Fine. But if one kid hugs me, I swear—" "Deal." She tossed a handful of change onto the table. "Let’s go practice our pirate laughs."
created_at
"2026-03-18T10:24:41.369Z"
3/18/2026, 10:24:41 AM
model
"mistralai/mistral-small-2603"
1/1/2603, 12:00:00 AM
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
370
moderation_latency
(null)
generation_time
11763
tokens_prompt
77
tokens_completion
1774
native_tokens_prompt
81
native_tokens_completion
1621
native_tokens_completion_images
(null)
native_tokens_reasoning
1467
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
0.00098475
router
(null)
provider_responses
0
endpoint_id
"f5ed6283-4e17-457d-98cd-2ec0c318171d"
id
"045279ed4a094f018f727d16bc83dbd3"
is_byok
false
latency
362
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-1773829481-1Emx2QVQCNj1Yh6Rk87N"
upstream_id
"045279ed4a094f018f727d16bc83dbd3"
total_cost
0.00098475
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
196
0.00%
Dialogue to Total Word Ratio
Ratio: 65.31%, Deviation: 24.69%
neededClean
false
wordsTotal
196
wordsDialogue
128
49.8722%