NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHXQ2PWP2VCDMQMR8BXWHGZ8
Run Details
Model:
Mistral Medium 3.1
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
5.3s
Cost:
$0.000698
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
82.88%
Dialogue to Total Word Ratio
(details)
91.4389%
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 *sure* this is the right house? Last time you ‘scouted,’ we ended up in a PTA meeting stealing baked goods.” Bill squinted at the balloon arch. “Positive. See the ‘Happy 8th, Timmy’ banner? That’s our guy. Rich kid. Probably got a PlayStation in every present.” “And we’re *sure* the parents won’t notice two adults who aren’t parents?” “Pfft. We’re in costumes. I’m a magician, you’re a clown. We blend right in.” Molly gestured to her polka-dot pants. “Bill, I look like a crime scene.” “Exactly! Distracting. Now, you cause a ruckus—knock over the piñata, start a food fight, whatever. I’ll ‘help’ the mom with the presents. Classic misdirection.” “What’s *my* cut if I’m the one getting cake frosting in my eyes?” “Sixty-forty. But if you eat any of the goldfish crackers, it’s fifty.” Molly sighed. “Fine. But if I have to make balloon animals, I’m charging extra.” Bill grinned. “Deal. Now let’s go ruin a child’s birthday.” He paused. “Wait—what’s our exit strategy?” Molly patted her wig. “Same as always. Scream ‘fire,’ grab the loot, and hope no one remembers the clown with a getaway scooter.”
created_at
"2026-02-20T14:25:52.547Z"
2/20/2026, 2:25:52 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
245
moderation_latency
(null)
generation_time
5244
tokens_prompt
77
tokens_completion
347
native_tokens_prompt
69
native_tokens_completion
335
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
0.0006976
router
(null)
provider_responses
0
endpoint_id
"13c5002b-8c5b-490c-8a5f-52ec0242804f"
id
"92fae3ab809d422984f927d75bc316c6"
is_byok
false
latency
245
model_permaslug
"mistralai/mistral-medium-3.1"
3/1/2001, 12:00:00 AM
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771597552-ol5usfVBAdkRBc2L80DE"
upstream_id
"92fae3ab809d422984f927d75bc316c6"
total_cost
0.0006976
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
82.88%
Dialogue to Total Word Ratio
Ratio: 83.42%, Deviation: 6.58%
neededClean
false
wordsTotal
199
wordsDialogue
166
91.4389%