NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHXQ1JXQ51X3BWRD9CSSK8Y4
Run Details
Model:
Mistral Medium 3.1
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
6.7s
Cost:
$0.000654
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
27.01%
Dialogue to Total Word Ratio
(details)
63.5028%
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 rainbow balloons bobbed cheerfully against the ceiling of the community center, taunting Molly from their perch outside the window. She adjusted her oversized clown wig and glared at Bill, who was currently wrestling with a pair of glitter-covered overalls. "You look like a disgruntled lollipop," she said. Bill yanked the straps up. "And you look like a mime who just found out miming isn’t a real job. Now, focus. We’ve got twenty minutes before the piñata gets whacked and half the parents start filming their kids’ ‘adorable’ meltdowns." Molly checked her watch. "Right. You take the gift table, I’ll hit the goodie bags. And remember—" "—no eye contact with the magician. Yeah, yeah. That guy’s got *vibes*." Bill cracked his knuckles. "What’s our exit strategy if some kid recognizes us from the *last* party we hit?" Molly grinned. "We blame the face paint. ‘Oh no, little Timmy, we’re *new* clowns! The *old* ones were definitely not felons.’" Bill sighed. "You’re enjoying this too much." A distant voice boomed over a microphone: *"And now, let’s all sing ‘Happy Birthday’ to little Emily!"* Molly grabbed Bill’s arm. "Showtime, partner. Try not to cry when they sing. It ruins the menace."
created_at
"2026-02-20T14:25:15.712Z"
2/20/2026, 2:25:15 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
282
moderation_latency
(null)
generation_time
6567
tokens_prompt
77
tokens_completion
330
native_tokens_prompt
69
native_tokens_completion
313
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
0.0006536
router
(null)
provider_responses
0
endpoint_id
"13c5002b-8c5b-490c-8a5f-52ec0242804f"
id
"7fc06a3389834d3ab72901e494bb0afd"
is_byok
false
latency
282
model_permaslug
"mistralai/mistral-medium-3.1"
3/1/2001, 12:00:00 AM
provider_name
"Mistral"
status
200
api_type
"completions"
id
"gen-1771597515-p9QLWsrIMn6St1pC3zaZ"
upstream_id
"7fc06a3389834d3ab72901e494bb0afd"
total_cost
0.0006536
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
201
27.01%
Dialogue to Total Word Ratio
Ratio: 60.70%, Deviation: 10.70%
neededClean
false
wordsTotal
201
wordsDialogue
122
63.5028%