NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-27-01M5YJ1TFASRAP9MV445Y34ZWB
Run Details
Model:
Kimi K3.1 Pro (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
5m 25s
Cost:
$0.114492
Provider:
Moonshot AI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 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 Bluebell Community Centre smelled of jelly, carpet cleaner, and impending litigation. Molly spread a colouring book across the bonnet of Bill’s van. On its cover, a smiling badger wore a waistcoat. Inside, she had drawn the party room, the kitchen, and a bouncy castle shaped like a dragon. Bill’s van had been white, but rust and an incident involving a pigeon sanctuary had given it the mottled appearance of a diseased loaf. A sign on its side read BILL’S BALLOONS: PARTIES, WEDDINGS, ESCAPES. Molly had crossed out ESCAPES with a marker after their last job, when Bill had driven into a hedge and apologised to it for twenty minutes without being asked. Bill peered at the dragon. “Why has it got eyebrows?” “Because it’s seen things.” Molly tapped the badger. “We go in as entertainers. You’re Captain Cupcake. I’m Professor Sprinkles.” “I wanted to be Professor Sprinkles.” “You get dizzy saying ‘sprinkles.’” He straightened his paper crown. “Fine. What’s my job?” “Stand near the presents and look festive.” “I can do festive.” “You waved at a funeral.” “I was being supportive.” Molly moved a button along the page. “At two, the magician starts. At three, they serve cake. At four, we leave with every parcel in the dragon.” Bill frowned. “Won’t the dragon notice?” “It’s inflatable.” “Good. I hate conflict.” She gave him a laundry bag printed with stars. “This is our sack.” “It says ‘Brian’s Washing.’” “Brian won’t miss it.” “Brian’s my landlord.” “Then he’ll appreciate the initiative.” From the centre came a shriek, followed by applause. Bill ducked behind the van. Molly sighed. “It’s a children’s party, not a police raid.” “Children are honest. That’s what makes them dangerous.” “If we get caught, we’re volunteers.” “Volunteers with a sack?” “Enthusiastic volunteers with sack experience.” Molly handed him a balloon dog. “If anyone questions you, make one of these.” Bill examined it. “What is it?” “A dog.” “It looks like a saxophone with anxiety.” “Then call it jazz.” He tucked it into his belt. “And the presents? How do we know they’re worth taking?” Molly checked the invitation. “The birthday boy’s father collects watches.” “So we’re robbing a child based on his father’s taste?” “We’re stealing opportunities, Bill.” “Opportunities don’t usually come wrapped in dinosaurs.” She folded the colouring book. “Remember: no grabbing, no running, and absolutely no crying.” “Why would I cry?” “You cried at the puppet show.” “The duck had lost his shop.” A woman opened the centre door and summoned them inside. Bill beamed. Molly lifted the sack. “Ready?” she whispered. “No,” said Bill. “But I am wearing supportive underwear.” They marched inside, where twenty children turned toward them. The birthday boy pointed at Bill’s crown. His verdict was swift and devastating. “The small one says I’m not a captain.” Bill looked at Molly. Molly looked at the presents. There were twelve, all small, and one was gently mooing. “Change of plan,” she murmured. “We steal the mooing one and reassess.” “Finally,” Bill whispered. “Leadership.”
created_at
"2026-10-27T11:31:11.477Z"
10/27/2026, 11:31:11 AM
model
"moonshotai/kimi-k3.1-pro-20261023"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1617
moderation_latency
(null)
generation_time
324468
tokens_prompt
75
tokens_completion
11298
native_tokens_prompt
146
native_tokens_completion
11420
native_tokens_completion_images
(null)
native_tokens_reasoning
10637
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
(null)
usage
0.114492
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.22.1; linux; x64))"
http_referer
(null)
request_id
"req-1793100671-uT7vqeMgmHoXPkVB9UPh"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1793100671-OTZK2W2Xi80OQUvOjmaW"
upstream_id
"chatcmpl-6ae08b80216bd289df217b85"
provider_responses
0
endpoint_id
"a3fafaac-f097-4ef1-86b3-842854dad5c6"
id
"chatcmpl-6ae08b80216bd289df217b85"
is_byok
false
latency
1617
model_permaslug
"moonshotai/kimi-k3.1-pro-20261023"
provider_name
"Moonshot AI"
status
200
total_cost
0.114492
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Moonshot AI"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
500
100.00%
Dialogue to Total Word Ratio
Ratio: 50.00%, Deviation: 0.00%
neededClean
false
wordsTotal
500
wordsDialogue
250
100.0000%