NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-06-01M48VW4RVXPR26H7RYBN302BA
Run Details
Model:
Mistral Large 4.0
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
13.3s
Cost:
$0.000746
Provider:
Mistral
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
0.18%
Dialogue to Total Word Ratio
(details)
49.7787%
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 party hat and whispered, "Bill, are you absolutely certain about this?" Bill tightened his clown nose. "The Johnson twins' birthday. Fifty kids. Unsupervised gift table. It's practically begging for professionals." "Professionals don't wear rainbow wigs to children's parties." "I'm method acting." Molly sighed. "The cake is at three. We have eleven minutes to locate the presents, identify valuables, and escape before the piñata." "Easy. I've already cased the basement. They keep everything in the utility closet behind the water heater." "You went to the house?" "I went to three houses. This one had the best security—meaning a golden retriever named Princess who loves belly rubs." Molly checked her watch. "What's the extraction plan?" Bill grinned, revealing a lollipop he'd somehow acquired. "I befriended the magician. He's our inside man. Says he'll 'accidentally' release doves during the chaos." "Doves?" "He misunderstood. It's pigeons. From the roof. Same effect." "Bill, we're stealing from children." "We're redistributing wealth to the criminally underpaid. There's a difference." The door burst open. A small girl pointed at them. "Mommy, why are those clowns whispering?" Bill winked. "Surprise inspection, sweetheart. Safety regulations." Molly grabbed his arm. "Run." They bolted, party hats flying, as fifty children screamed with delight.
created_at
"2026-10-06T15:03:51.842Z"
10/6/2026, 3:03:51 PM
model
"mistralai/mistral-large-4-0-20261006"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
918
moderation_latency
(null)
generation_time
13302
tokens_prompt
75
tokens_completion
360
native_tokens_prompt
79
native_tokens_completion
331
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)
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
0.00074551
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791299031-Xhe7ZxrThYgjBi0xSRCm"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791299031-6VSUjJtOupicodN45Idq"
upstream_id
"c3bcc612e71045fab42883af468cd0ed"
provider_responses
0
endpoint_id
"19b3b5d7-23f6-4b63-8109-64a6cc37d996"
id
"c3bcc612e71045fab42883af468cd0ed"
is_byok
false
latency
918
model_permaslug
"mistralai/mistral-large-4-0-20261006"
provider_name
"Mistral"
status
200
total_cost
0.00074551
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
99.38%
Matches word count
n/a
neededClean
false
words
205
0.18%
Dialogue to Total Word Ratio
Ratio: 74.15%, Deviation: 15.85%
neededClean
false
wordsTotal
205
wordsDialogue
152
49.7787%