NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM07SV0191WR19D68ZW152M2
Run Details
Model:
Mistral Small 4
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3.2s
Cost:
$0.000184
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
46.8248%
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 adjusted her rainbow wig in the rearview mirror, the van’s engine humming like a disgruntled stomach. "You sure this is the place?" Bill squinted at the house, wrapped in enough pastel-colored streamers to choke a clown. "Positive. Birthday parties are soft targets. Moms are tipsy, dads are pretending to understand princess-themed trivia, kids are too busy eating cake to notice a thing." Molly popped a bubblegum bubble. "What’s the play?" Bill ticked off on his fingers. "Phase one: You act as the overenthusiastic clown. Phase two: I ‘accidentally’ spill glitter dust everywhere. Phase three: While everyone’s sneezing and laughing, we redirect the treasure chest to the getaway van." Molly frowned. "I hate clowns." "Since when?" "Since always. They look like serial killers who took a bad acid trip." Bill sighed, grabbing a whoopee cushion from the glove box. "Fine. You can be the ‘sneaky elf’ who just ‘really loves gifts.’ Just look pretty and point at things." Molly grabbed the cushion and held it to his face like a knife. "I *am* pretty. And if you mess this up, I’m cushioning your parachute for the leap off the nearest bridge."
created_at
"2026-03-18T10:28:00.14Z"
3/18/2026, 10:28:00 AM
model
"mistralai/mistral-small-2603"
1/1/2603, 12:00:00 AM
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
540
moderation_latency
(null)
generation_time
3102
tokens_prompt
77
tokens_completion
310
native_tokens_prompt
81
native_tokens_completion
286
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
0.00018375
router
(null)
provider_responses
0
endpoint_id
"f5ed6283-4e17-457d-98cd-2ec0c318171d"
id
"5630f33487bf406a9a4365a620b69b7c"
is_byok
false
latency
540
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-1773829680-Ai3ZzDlfN2ptnV5CW1aV"
upstream_id
"5630f33487bf406a9a4365a620b69b7c"
total_cost
0.00018375
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
93.65%
Matches word count
n/a
neededClean
false
words
191
0.00%
Dialogue to Total Word Ratio
Ratio: 64.77%, Deviation: 25.23%
neededClean
false
wordsTotal
193
wordsDialogue
125
46.8248%