NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHXPH8SH7BYMQZ19DCFAZYXY
Run Details
Model:
Mistral Medium 3.1
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
5.6s
Cost:
$0.000664
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
60.28%
Matches word count
(details)
99.65%
Dialogue to Total Word Ratio
(details)
79.9629%
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 oversized clown wig and glared at Bill. “You’re telling me the *best* time to hit the piñata stash is *during* the cake?” Bill wiped frosting from his fake mustache. “Kid’s blowing out candles, parents are distracted, magician’s setting himself on fire—classic misdirection. We’re in, we’re out, we’re rich in Funbucks and whatever the hell a *Squishmallow* is.” “And if we get caught?” “Please. We’re dressed as a clown and a *very* convincing giraffe. Who’s gonna suspect *us*?” Molly sighed. “The giraffe costume was *your* idea. I look like a drunk spot check.” “You *are* a drunk spot check. Now focus—you grab the LEGO sets, I’ll hit the gift cards. And if anyone asks, we’re ‘entertainment.’” “What’s our act?” Bill grinned. “Improv. You juggle, I pretend to be your manager.” “Bill, I can’t juggle.” “Then *improvise*! Throw a kid’s juice box in the air and look panicked. Works every time.” Molly groaned. “This is why we’re not invited to real heists.” “Oh, we’re invited. We just keep getting *un*-invited. Now move—kids are singing *Happy Birthday* and I *hate* that song.”
created_at
"2026-02-20T14:16:21.05Z"
2/20/2026, 2:16:21 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
277
moderation_latency
(null)
generation_time
5360
tokens_prompt
77
tokens_completion
329
native_tokens_prompt
69
native_tokens_completion
318
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
0.0006636
router
(null)
provider_responses
0
endpoint_id
"13c5002b-8c5b-490c-8a5f-52ec0242804f"
id
"f3e6a252f18a4b5fbeefbceaa17be805"
is_byok
false
latency
275
model_permaslug
"mistralai/mistral-medium-3.1"
3/1/2001, 12:00:00 AM
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771596981-3agSpR8qZ8MoMZzVwvp0"
upstream_id
"f3e6a252f18a4b5fbeefbceaa17be805"
total_cost
0.0006636
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
60.28%
Matches word count
n/a
neededClean
false
words
185
99.65%
Dialogue to Total Word Ratio
Ratio: 87.57%, Deviation: 2.43%
neededClean
false
wordsTotal
185
wordsDialogue
162
79.9629%