NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-27-01M5YHT1MBG4Y8CEH3MNSH6NEH
Run Details
Model:
Kimi K3.1 Pro (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
8m 32s
Cost:
$0.178172
Provider:
Moonshot AI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.93%
Dialogue to Total Word Ratio
(details)
99.9643%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 70% 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 plan across the steering wheel, anchoring one corner with a doughnut and the other with Bill’s hand. Beyond the windscreen, Sunnybrook Village Hall glittered with balloons, bunting, and the sort of happiness that made her teeth itch. A banner read HAPPY SIXTH BIRTHDAY, POPPY! Beneath it, presents rose like a small, expensive alp. “Tell me we’re not robbing children,” Bill said. “We’re robbing Santa.” “That makes it feel almost traditional.” Bill peered through binoculars. “I count thirty-two parcels, one clown, and a sausage dog wearing a waistcoat.” “The dog’s our main problem. Clowns can be negotiated with.” “Can they?” “Not with dignity. Now, phase one: you wheel in the empty catering trolley and tell them you’re Bongo, the birthday bear.” Bill lifted a furry head from the footwell. “Why am I Bongo?” “Because the bear suit fits you, and because my mother didn’t raise me to be ridiculous before lunch.” “Your mother raised you to forge library cards.” “She believed in literacy. Phase two: I enter as Madam Zaza, children’s entertainer. While I distract everyone with balloon modelling, you load the trolley.” “What balloons?” Molly displayed three sad, shapeless rubber loops. “These.” “That’s a worm being sick.” “It’s a giraffe if the child has imagination. Phase three: I announce that Poppy’s final surprise is outside. Everybody stampedes into the garden. You take the trolley through the kitchen, I collect you at the side gate, and we’re away before the jelly sets.” Bill studied the diagram. “You’ve drawn our escape through a bouncy castle.” “That’s not a bouncy castle. That’s the vicar.” “Why is the vicar wearing a tiara?” “Fancy dress. The invitation says ‘Princesses and Pirates.’” Bill slowly looked at the bear head. “Then why have you got me dressed as wildlife?” “Versatility.” “And what are you wearing?” Molly produced an eyepatch, a plastic parrot, and a tutu. “Princess pirate.” “Of course. What if someone asks Madam Zaza to perform magic?” “I’ll make the clown disappear.” “How?” “I’ll pay him to leave. He’s already offered. Says the dog knows where he lives.” Bill folded the plan. “This is our worst idea since we robbed the aquarium.” “We got a penguin.” “We got a fine and a penguin-related restraining order.” Somebody inside cheered. A woman waved from the doorway, mistaking them for the entertainment, and Molly waved back with the serene confidence of a woman holding three dead balloons. “They think we’re entertainers.” “Excellent. Phase one’s started.” “Molly, I can’t dance.” “You’re a bear. Look disappointed and occasionally point at nothing. Children adore that.” Bill pulled on the head. “What does Bongo do?” “Birthdays, mostly. Try not to get attached to the presents.” “And if the dog arrests us?” “Plead insanity. Your bear head is compelling.” Bill looked through the eyeholes, then pointed towards the hall. “One last thing.” “What?” “The real Bongo just arrived.” Molly did not blink. “Change of plan. You’re Bongo’s brother. Look festive, and don’t mention the penguin until we’ve got all the presents.”
created_at
"2026-10-27T11:26:56.661Z"
10/27/2026, 11:26:56 AM
model
"moonshotai/kimi-k3.1-pro-20261023"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2016
moderation_latency
(null)
generation_time
511582
tokens_prompt
75
tokens_completion
17796
native_tokens_prompt
146
native_tokens_completion
17788
native_tokens_completion_images
(null)
native_tokens_reasoning
17005
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
0.178172
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.22.1; linux; x64))"
http_referer
(null)
request_id
"req-1793100416-q0cGJvcq7DRjo76vVQ4Y"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1793100416-c363XWvn9rn7AUWovDUV"
upstream_id
"chatcmpl-6ae08a8187f6827cf5a21f57"
provider_responses
0
endpoint_id
"a3fafaac-f097-4ef1-86b3-842854dad5c6"
id
"chatcmpl-6ae08a8187f6827cf5a21f57"
is_byok
false
latency
2016
model_permaslug
"moonshotai/kimi-k3.1-pro-20261023"
provider_name
"Moonshot AI"
status
200
total_cost
0.178172
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
99.93%
Dialogue to Total Word Ratio
Ratio: 70.12%, Deviation: 0.12%
neededClean
false
wordsTotal
502
wordsDialogue
352
99.9643%