NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHXQ8A1RWKKW2EZ4T3JYP8SZ
Run Details
Model:
Mistral Medium 3.1
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
3.9s
Cost:
$0.000686
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
70.46%
Dialogue to Total Word Ratio
(details)
83.2233%
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 against the ceiling of the community center like overcaffeinated jellyfish as Molly adjusted her oversized clown wig in the parking lot. Bill fiddled with a walkie-talkie that looked like it had been salvaged from a 1980s police auction. “You sure this is the right place?” Bill muttered, squinting at the hand-painted sign that read *LITTLE TREASURES DAYCARE—JASPER’S 5TH BIRTHDAY BASH!* Molly rolled her eyes. “Oh, yeah, because the other daycare with a bouncy castle shaped like a dragon *definitely* has the same level of loot. Use your brain, Bill.” “My brain says stealing from kids is morally ambiguous.” “Your brain also thought ‘disguising ourselves as a magician and his assistant’ was a good idea.” She gestured to his sequined cape. “You look like a glittery bat who lost a fight with a bedazzler.” Bill adjusted his cape with dignity. “I’ll have you know, this cape has *pockets*. Essential for quick grabs.” Molly cracked her knuckles. “Alright, here’s the play: I ‘accidentally’ knock over the gift table while doing my ‘hilarious’ balloon animal routine. You ‘help’ me clean up by shoving everything into those *essential* pockets.” Bill grinned. “And if someone asks?” Molly tossed him a whoopee cushion. “We blame the clown.”
created_at
"2026-02-20T14:28:56Z"
2/20/2026, 2:28:56 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
254
moderation_latency
(null)
generation_time
3728
tokens_prompt
77
tokens_completion
355
native_tokens_prompt
69
native_tokens_completion
329
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
0.0006856
router
(null)
provider_responses
0
endpoint_id
"13c5002b-8c5b-490c-8a5f-52ec0242804f"
id
"3b8ba424d4f646678ff917363995436e"
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-1771597736-9WX0GXXa0SscURwOlQce"
upstream_id
"3b8ba424d4f646678ff917363995436e"
total_cost
0.0006856
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
95.99%
Matches word count
n/a
neededClean
false
words
208
70.46%
Dialogue to Total Word Ratio
Ratio: 57.69%, Deviation: 7.69%
neededClean
false
wordsTotal
208
wordsDialogue
120
83.2233%