NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM09WDTE8EG1E5EH7ZDYHX5Q
Run Details
Model:
Mistral Small 4
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
4.0s
Cost:
$0.000210
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
81.27%
Matches word count
(details)
0.02%
Dialogue to Total Word Ratio
(details)
40.6487%
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 bunny ears and squinted at the party flyer taped to the community center window. "You sure this is the right place? The flyer says 'Under-the-Sea Adventure,' but there's no treasure chest in sight." Bill rolled his eyes. "It's a metaphor, genius. The presents are the treasure." "I know that," Molly scoffed. "But look—there's a clown out front handing out balloons. Clowns mean cops, Bill. History." Bill tugged his pirate hat lower. "Relax. No cop’s gonna suspect a couple of *literal* pirates crashing a kids' party." He checked his watch. "Show starts in ten. We go in as clown-enhanced looters." Molly groaned. "Clown *enhanced*? That sounds even worse." "Fine," Bill muttered. "We go in as *uncle* and *aunt* who got lost at the buffet." Molly brightened. "Now you're talking. I *do* look great in aunt energy." She patted her frizzy wig. "You sure about the escape plan, though? The dumpster’s sketchy." Bill tossed her a roll of duct tape. "Dumpster’s our best shot. We fill the bags, toss ‘em in, climb out the back door like normal guests. No alarms, no drama." Molly bit her lip. "What if a kid sees us?" Bill grinned. "Then we tell them to close their eyes and make a wish. Works every time."
created_at
"2026-03-18T11:04:22.108Z"
3/18/2026, 11:04:22 AM
model
"mistralai/mistral-small-2603"
1/1/2603, 12:00:00 AM
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
451
moderation_latency
(null)
generation_time
3914
tokens_prompt
77
tokens_completion
326
native_tokens_prompt
81
native_tokens_completion
330
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
0.00021015
router
(null)
provider_responses
0
endpoint_id
"f5ed6283-4e17-457d-98cd-2ec0c318171d"
id
"263ca830fa474c7baaaa777118060f91"
is_byok
false
latency
451
model_permaslug
"mistralai/mistral-small-2603"
1/1/2603, 12:00:00 AM
provider_name
"Mistral"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1773831862-TWggCnharjd6VpUZeW77"
upstream_id
"263ca830fa474c7baaaa777118060f91"
total_cost
0.00021015
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
Evaluation details
Result
Evaluator
Details
Meta Data
81.27%
Matches word count
n/a
neededClean
false
words
212
0.02%
Dialogue to Total Word Ratio
Ratio: 73.02%, Deviation: 16.98%
neededClean
false
wordsTotal
215
wordsDialogue
157
40.6487%