NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHXPJYX6BSYB6JPXCM3KZMPG
Run Details
Model:
Mistral Medium 3.1
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
9.8s
Cost:
$0.000636
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
12.13%
Dialogue to Total Word Ratio
(details)
55.7548%
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 neon glow of the *"Happy 8th Birthday, Timmy!"* sign flickered through the miniblinds as Molly adjusted her oversized clown nose. "You realize we’re about to commit felony theft from a room full of sugar-crazed seven-year-olds, right?" Bill tugged at his itchy elf costume, the jingle bells on his shoes sounding like a tiny alarm system. "Relax. Kids are terrible witnesses. Half of ‘em still think the Tooth Fairy’s real. We’ll be in and out before the piñata’s empty." Molly eyed the gift table groaning under mountains of wrapping paper. "What’s our play? Distraction?" "Obviously." Bill pulled a kazoo from his pocket. "I hit ‘em with a rousing rendition of *Baby Shark*, you load up the sack. Classic misdirection." "Your kazoo skills are *not* a reliable distraction." "Fine. Plan B." He tossed her a whoopee cushion. "You plant this on the birthday boy’s chair. Chaos ensues. We vanish like glitter in a vacuum." Molly sighed. "We’re the worst criminals ever." Bill grinned. "Nah. We’re the *best* at being the worst." He cracked the door. The shriek of twenty children mid-"Musical Chairs" spilled out. "Showtime, partner. Try not to traumatize ‘em *too* much."
created_at
"2026-02-20T14:17:16.466Z"
2/20/2026, 2:17:16 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
4204
moderation_latency
(null)
generation_time
9721
tokens_prompt
77
tokens_completion
315
native_tokens_prompt
69
native_tokens_completion
304
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
0.0006356
router
(null)
provider_responses
0
endpoint_id
"13c5002b-8c5b-490c-8a5f-52ec0242804f"
id
"a8cb6abd56ce43c1848df2c987b81d33"
is_byok
false
latency
4204
model_permaslug
"mistralai/mistral-medium-3.1"
3/1/2001, 12:00:00 AM
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771597036-uXx5ml7b8lP0It8JezCZ"
upstream_id
"a8cb6abd56ce43c1848df2c987b81d33"
total_cost
0.0006356
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
99.38%
Matches word count
n/a
neededClean
false
words
195
12.13%
Dialogue to Total Word Ratio
Ratio: 62.05%, Deviation: 12.05%
neededClean
false
wordsTotal
195
wordsDialogue
121
55.7548%