NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-07-01M4ATVPZ7Y4J77HAQE7JN5KN2
Run Details
Model:
Mistral Large 4.0 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 25s
Cost:
$0.016749
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
60.28%
Matches word count
(details)
91.23%
Dialogue to Total Word Ratio
(details)
75.7514%
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
Molly spread the crayon-drawn floor plan across the wobbly kitchen table, pointing at the glitter stain with a grease pencil. The paper smelled faintly of juice boxes. "The cake's at 3 PM. We hit the gift table while the sugar rush hits." Bill squinted at the childish diagram, his eyebrows climbing toward his hairline. He tapped the table nervously. "You want to rob a seven-year-old's birthday party?" "It's not robbery if they're distracted," Molly said, adjusting her ski mask over her messy bun. "Think of it as redistributing joy." Bill rubbed his temples with trembling fingers. "Last time at the retirement home, we got chased by a walker." "That was different. These are children. They'll believe anything." Molly pulled out a rusty grappling hook from her utility belt, testing the spring. "I'm going through the window. You create a distraction." "With what?" "Confetti. Lots of confetti." "That's not a distraction, that's evidence." Molly grinned, holding up a handful of cheap party hats. "Trust me. I've done recon. The pinata is filled with candy, Bill. Real candy. We could retire on that alone." Bill sighed, picking up a squeaky party horn from the counter. "Fine. But if we get caught, I'm blaming you entirely." "Obviously. Now, synchronize watches. We move when the Happy Birthday song hits."
created_at
"2026-10-07T09:24:38Z"
10/7/2026, 9:24:38 AM
model
"mistralai/mistral-large-4-0-20261006"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1928
moderation_latency
(null)
generation_time
85123
tokens_prompt
75
tokens_completion
7159
native_tokens_prompt
67
native_tokens_completion
7992
native_tokens_completion_images
(null)
native_tokens_reasoning
6822
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
service_tier
"default"
usage
0.01674884
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791365078-AXFwXAXPKkAi6b3XXySW"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791365078-ay8k3hnUh3yCyipYJLRk"
upstream_id
"5215661e9f0241b8a97d0a3a2007b2ed"
provider_responses
0
endpoint_id
"19b3b5d7-23f6-4b63-8109-64a6cc37d996"
id
"5215661e9f0241b8a97d0a3a2007b2ed"
is_byok
false
latency
547
model_permaslug
"mistralai/mistral-large-4-0-20261006"
provider_name
"Mistral"
status
200
total_cost
0.01674884
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Mistral"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
60.28%
Matches word count
n/a
neededClean
false
words
215
91.23%
Dialogue to Total Word Ratio
Ratio: 55.50%, Deviation: 5.50%
neededClean
false
wordsTotal
218
wordsDialogue
121
75.7514%