NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0838FVF6R4PQ66QRFV8ERP
Run Details
Model:
Mistral Small 4 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
54.3s
Cost:
$0.005590
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
99.81%
Dialogue to Total Word Ratio
(details)
99.8986%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 McGillicuddy backyard was pure, unfiltered bedlam. Juice boxes formed treacherous stepping stones across the lawn, and the inflatable bounce house groaned under the assault of six sugar-crazed seven-year-olds. Their screams were less joyful noise and more auditory warfare, capable of summoning the authorities—or at least summoning a headache the size of Texas. Across the yard, the parents were locked in a deathmatch with a clown whose rainbow wig had declared bankruptcy. His oversized shoes squeaked with every exaggerated step, and his face paint told a tragic story of artistic ambition gone horribly wrong. Bill crept forward, his ski mask barely clinging to one ear like a lost dog collar. He adjusted it with a grumble. "Ready?" Molly gave him a withering look. "After what happened last time? Never." Molly adjusted her bobby pin with the precision of a heart surgeon—or someone who had watched one too many true crime documentaries at 3 AM. "Presents unwatched. Alarm’s a Chihuahua named Satan. Bites." Bill peeked through the living room window. A child in fairy wings rode a tricycle directly into a tower of paper plates. A cactus-themed pop song warbled at maximum volume. He exhaled sharply. "Jail."
created_at
"2026-03-18T10:33:08.874Z"
3/18/2026, 10:33:08 AM
model
"mistralai/mistral-small-2603"
1/1/2603, 12:00:00 AM
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
404
moderation_latency
(null)
generation_time
54213
tokens_prompt
77
tokens_completion
9166
native_tokens_prompt
81
native_tokens_completion
9297
native_tokens_completion_images
(null)
native_tokens_reasoning
8850
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
0.00559035
router
(null)
provider_responses
0
endpoint_id
"f5ed6283-4e17-457d-98cd-2ec0c318171d"
id
"bb053a5ccb2342bb948e0ae8149f7deb"
is_byok
false
latency
391
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-1773829988-NLEBCYwJxMvbsO6HoF1y"
upstream_id
"bb053a5ccb2342bb948e0ae8149f7deb"
total_cost
0.00559035
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
198
99.81%
Dialogue to Total Word Ratio
Ratio: 7.92%, Deviation: 2.08%
neededClean
false
wordsTotal
202
wordsDialogue
16
99.8986%