NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0A6DTKAD7NAWMAYGPE2YK7
Run Details
Model:
Mistral Small 4
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
3.1s
Cost:
$0.000190
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
99.52%
Dialogue to Total Word Ratio
(details)
97.7542%
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 adjusted the ski mask over her eyes and checked the duffel bag on the floor. "You sure this is the right place?" she asked, eyeing the bright balloons tied to the fence. "Kids’ party. Balloons. Cake shaped like a dinosaur." Bill didn’t look up from his phone. "Nah, this is it. Address checked out." He pointed to the sign on the porch—*Happy 5th Birthday, Timmy!*—and then to the sliding glass door, which was slightly ajar. "No alarm. Easy entry." Molly groaned. "No alarm? That’s sketchy. Who doesn’t have an alarm these days?" She pulled a pair of black gloves from her pocket and snapped them on. "What if the kid’s in there? What if he’s hiding under the snack table?" Bill stuffed the bag with tools. "It’s a kids’ party. The parents are probably too busy herding toddlers to notice us." He grinned. "And if we see a kid? Distraction protocol." Molly raised an eyebrow. "What, we buy a piñata and swing it at their legs?" "Or we sing ‘Happy Birthday’ real loud and blame the echo." Bill shouldered the bag. "Come on, before the cake’s gone." He stepped toward the door, paused, and turned back. "You bringing the noise-canceling headphones?" Molly patted her ear. "Already on."
created_at
"2026-03-18T11:09:49.792Z"
3/18/2026, 11:09:49 AM
model
"mistralai/mistral-small-2603"
1/1/2603, 12:00:00 AM
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
443
moderation_latency
(null)
generation_time
3009
tokens_prompt
77
tokens_completion
319
native_tokens_prompt
81
native_tokens_completion
310
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
0.00018951
router
(null)
provider_responses
0
endpoint_id
"f5ed6283-4e17-457d-98cd-2ec0c318171d"
id
"5d74870a6bab4ce2b196f3787bb75a17"
is_byok
false
latency
443
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-1773832189-1ZBcW9Rj9sR65FnZuBqU"
upstream_id
"5d74870a6bab4ce2b196f3787bb75a17"
total_cost
0.00018951
cache_discount
0.00000864
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
95.99%
Matches word count
n/a
neededClean
false
words
208
99.52%
Dialogue to Total Word Ratio
Ratio: 52.63%, Deviation: 2.63%
neededClean
false
wordsTotal
209
wordsDialogue
110
97.7542%