NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM09RVQPGWFH8MKX2NNPCZC7
Run Details
Model:
Mistral Small 4 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
5.8s
Cost:
$0.000446
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
13.42%
Dialogue to Total Word Ratio
(details)
6.7105%
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 and Bill sat in the back of their van, surrounded by maps and sketches of the party venue. Molly held the schematics of the building, her brow furrowed in concentration. "We can't just walk in the front door," Bill said, munching on a sandwich. "Obviously," Molly replied, rolling her eyes. "We'll pose as caterers. It's perfect." Bill choked on his sandwich. "Caterers? Have you seen my tie? I look like a guy who steams vegetables, not one who carries silver platters." Molly snatched the bread from his hand. "Fine, we'll be clowns. No one suspects clowns." "But we're not funny!" Bill protested. "We're criminals. We specialize in, like, jewel heists and bank jobs." "Exactly! We're versatile." Molly tapped the map. "We go in at the height of the cake cutting. Everyone's distracted, kids are screaming, parents are clapping—perfect cover." Bill sighed. "What if someone recognizes us?" "Then we say we're new in town. Or cousins of the birthday kid." Molly grinned. "Trust me, Bill. This'll work."
created_at
"2026-03-18T11:02:25.285Z"
3/18/2026, 11:02:25 AM
model
"mistralai/mistral-small-2603"
1/1/2603, 12:00:00 AM
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
517
moderation_latency
(null)
generation_time
5716
tokens_prompt
77
tokens_completion
768
native_tokens_prompt
81
native_tokens_completion
723
native_tokens_completion_images
(null)
native_tokens_reasoning
501
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
0.00044595
router
(null)
provider_responses
0
endpoint_id
"f5ed6283-4e17-457d-98cd-2ec0c318171d"
id
"fef16a93a12f4afca3176a5f2235ab06"
is_byok
false
latency
514
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-1773831745-IuAu3shVzmeEEPmEbXAq"
upstream_id
"fef16a93a12f4afca3176a5f2235ab06"
total_cost
0.00044595
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
168
13.42%
Dialogue to Total Word Ratio
Ratio: 61.90%, Deviation: 11.90%
neededClean
false
wordsTotal
168
wordsDialogue
104
6.7105%