NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHXQD8APZ0PSHR689X11KHVX
Run Details
Model:
Mistral Medium 3.1
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
18.7s
Cost:
$0.000600
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
0.40%
Dialogue to Total Word Ratio
(details)
50.2002%
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
The rainbow balloons bobbed cheerfully against the ceiling of the community center, taunting Molly from their perch outside the window. She adjusted her oversized clown nose—stolen from a dollar store—and shot Bill a look. "You’re sure the security here is just a guy named Gary who eats too many cupcakes?" Bill wiped orange face paint off his sleeve, leaving a smear on his already questionable Santa beard. "Positive. Guy’s got a nap schedule tighter than the vault at Fort Knox. We’ve got twenty minutes before he waddles back from the snack table." Molly cracked her knuckles. "Alright, but if we get caught, I’m blaming the beard. You look like a mall Santa who lost a fight with a lawnmower." "Better than you in that clown getup. You’re giving kids nightmares before we even steal their LEGOs." Bill jiggled the back door handle. "Lock’s already picked. You take the gift table, I’ll hit the piñata stash. And *do not* eat any of the cake." Molly gasped. "That’s just cruel. What kind of monster skips cake?" "The kind that doesn’t leave crumbs at a crime scene." Bill sighed. "Ten seconds. Ready?" Molly grinned. "Born ready. Let’s ruin some birthdays."
created_at
"2026-02-20T14:31:38.078Z"
2/20/2026, 2:31:38 PM
model
"mistralai/mistral-medium-3.1"
3/1/2001, 12:00:00 AM
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
251
moderation_latency
(null)
generation_time
18579
tokens_prompt
77
tokens_completion
311
native_tokens_prompt
69
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
0.0005996
router
(null)
provider_responses
0
endpoint_id
"13c5002b-8c5b-490c-8a5f-52ec0242804f"
id
"fa5b114a614c470dbc7e7d04d61b8fa0"
is_byok
false
latency
251
model_permaslug
"mistralai/mistral-medium-3.1"
3/1/2001, 12:00:00 AM
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771597898-8SzLMgCRSLq1C1g1KdRC"
upstream_id
"fa5b114a614c470dbc7e7d04d61b8fa0"
total_cost
0.0005996
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
199
0.40%
Dialogue to Total Word Ratio
Ratio: 65.33%, Deviation: 15.33%
neededClean
false
wordsTotal
199
wordsDialogue
130
50.2002%