NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM08T13KFEJB6Q5TB9HBAFVA
Run Details
Model:
Mistral Small 4
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
3.0s
Cost:
$0.000178
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
75.16%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
37.5778%
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 rain tapped a lazy rhythm against the alleyway dumpster as Molly wiped grease from her palms with a rag that had long since given up on cleanliness. Beside her, Bill adjusted the straps of his too-small elf costume with a grimace, the jingle bells on the hat he’d bought at the thrift store sounding like a dying wind chime. It’s perfect," Molly said, eyeing the back door of the community center bathed in the flickering light of a broken neon safety sign. The lock was a joke, the kind that surrendered to a credit card and a prayer. Bill snickered, the sound muffled behind his fake beard, and muttered about how he hadn’t signed up to dress like a reject from Santa’s workshop. Molly ignored him, already fishing for her lockpicks. The presents were waiting—stuffed pandas, glittery jewelry kits, and at least three tablets disguised as Elsa wands. They’d be rich before the confetti even settled from the opening act of some exhausted clown. The lock clicked. Bill’s bells jangled as he shoved the door wider, revealing rows of unwrapped toys and a stage set for painfully rehearsed renditions of "Baby Shark." Molly grinned, heist adrenaline coursing through her. Time to turn childhood joy into a deposit at the pawn shop.
created_at
"2026-03-18T10:45:34.976Z"
3/18/2026, 10:45:34 AM
model
"mistralai/mistral-small-2603"
1/1/2603, 12:00:00 AM
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
431
moderation_latency
(null)
generation_time
2911
tokens_prompt
77
tokens_completion
314
native_tokens_prompt
81
native_tokens_completion
277
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
0.00017835
router
(null)
provider_responses
0
endpoint_id
"f5ed6283-4e17-457d-98cd-2ec0c318171d"
id
"1d2862f90944476491ef827c9b204181"
is_byok
false
latency
431
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-1773830734-5PaWMejU4scvGmHiCkmk"
upstream_id
"1d2862f90944476491ef827c9b204181"
total_cost
0.00017835
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
75.16%
Matches word count
n/a
neededClean
false
words
213
0.00%
Dialogue to Total Word Ratio
Ratio: 71.03%, Deviation: 61.03%
neededClean
false
wordsTotal
214
wordsDialogue
152
37.5778%