NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHXPGCBGF6TCCVGJ2P42QBBB
Run Details
Model:
Mistral Medium 3.1
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
4.8s
Cost:
$0.000626
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
6.18%
Dialogue to Total Word Ratio
(details)
51.0843%
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* disguise you could come up with is a guy in a dinosaur costume?” Bill flexed his foam T-Rex arms. “Kids love dinosaurs. I blend in. Also, limited peripheral vision—perfect for plausible deniability.” “You look like a drunk mascot from a failed theme park.” “And you look like a serial killer who raided a party store. That wig’s *haunting*.” Molly smoothed it down. “Focus. We’ve got twenty minutes before the piñata distraction. You grab the gift table, I’ll hit the goodie bags. And *do not* eat the cake.” “No promises. What if it’s Funfetti?” “Bill.” “Fine. But if I see a kid crying over a stolen My Little Pony, I’m throwing you under the bounce house.” Molly checked her watch. “Clock’s ticking. Remember—we’re *entertainers*, not criminals.” Bill adjusted his tail. “Right. Just two very committed performers… who definitely didn’t case this joint yesterday during storytime.” A balloon popped in the distance. Molly grinned. “Showtime, Rex.” Bill groaned. “I *hate* you.” He waddled toward the gift table. “Hey, kid. Ever seen a dinosaur do the cha-cha?”
created_at
"2026-02-20T14:15:51.932Z"
2/20/2026, 2:15:51 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
281
moderation_latency
(null)
generation_time
4742
tokens_prompt
77
tokens_completion
337
native_tokens_prompt
69
native_tokens_completion
299
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
0.0006256
router
(null)
provider_responses
0
endpoint_id
"13c5002b-8c5b-490c-8a5f-52ec0242804f"
id
"c8942d5d82a34682a8e61be43dad3310"
is_byok
false
latency
281
model_permaslug
"mistralai/mistral-medium-3.1"
3/1/2001, 12:00:00 AM
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771596951-8UGD7TaBWgY7PQhqdQc9"
upstream_id
"c8942d5d82a34682a8e61be43dad3310"
total_cost
0.0006256
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
192
6.18%
Dialogue to Total Word Ratio
Ratio: 77.08%, Deviation: 12.92%
neededClean
false
wordsTotal
192
wordsDialogue
148
51.0843%