NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHXPDS4QXGW1P1ZK9YE7ATZ1
Run Details
Model:
Mistral Medium 3.1
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
5.7s
Cost:
$0.000658
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 rainbow-bright piñata swayed ominously in the breeze, its papier-mâché grin taunting Molly from across the backyard. She adjusted her oversized "Party Mom" name tag—*Hello! My name is CAROL (but call me Mom!)*—and sidled up to Bill, who was currently pretending to be deeply invested in a game of "Pin the Tail on the Donkey" while actually casing the gift table. "Three o’clock," Molly muttered, nodding toward the mountain of wrapped boxes. "That one’s got the weight of a gold bar, and the other’s rattling like a cartful of rare Pokémon cards." Bill scratched his fake dad-beard, which was already peeling at the edges. "Kid in the Spider-Man costume’s been eyeing the same ones. Might be a problem." "Then we make him *not* a problem." Molly plucked a juice box from the snack table and casually upended it over the kid’s head. As he shrieked and bolted for his mom, she turned back to Bill. "Clock’s ticking. Magician’s setting up, which means parents’ll be distracted in—" she checked her watch, "*—nine minutes." Bill cracked his knuckles. "Enough time to grab the loot and blame it on the clown?" Molly smirked. "Clown’s already crying in the bathroom. Perfect patsy." She tossed him a party hat. "Let’s go ruin some childhoods."
created_at
"2026-02-20T14:14:26.724Z"
2/20/2026, 2:14:26 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
226
moderation_latency
(null)
generation_time
5512
tokens_prompt
77
tokens_completion
333
native_tokens_prompt
69
native_tokens_completion
315
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
0.0006576
router
(null)
provider_responses
0
endpoint_id
"13c5002b-8c5b-490c-8a5f-52ec0242804f"
id
"82db39fab4514fbe87a6594f2c892cc2"
is_byok
false
latency
226
model_permaslug
"mistralai/mistral-medium-3.1"
3/1/2001, 12:00:00 AM
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771596866-ZVZYHAuoe57nchOaGsec"
upstream_id
"82db39fab4514fbe87a6594f2c892cc2"
total_cost
0.0006576
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: 42.25%, Deviation: 32.25%
neededClean
false
wordsTotal
213
wordsDialogue
90
37.5778%