NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-27-01M5YFMFGT2ZPESND7CQAY9YF6
Run Details
Model:
Kimi K3.1 Pro (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
2m 59s
Cost:
$0.061622
Provider:
Moonshot AI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
72.98%
Dialogue to Total Word Ratio
(details)
86.4896%
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 birthday invitation across the bonnet of Bill’s van. It was printed with a smiling dinosaur and smelled faintly of jam. “Remember,” Bill said, “we go in as entertainers, grab the presents, and leave before anyone notices.” “Your last entertainer costume had a buckle that played ‘Yankee Doodle.’” “It was a tactical buckle.” “It played during a funeral.” Bill folded his arms. “This party’s different. Six-year-olds. Tiny attention spans. We’ll be invisible.” “You’ll be wearing a sequinned waistcoat and carrying a cardboard rabbit.” “Exactly. Camouflage.” Molly tapped the invitation. “The party starts at two. There’s a bouncy castle, a puppet show, and something called Captain Cupcake.” “Is Captain Cupcake a person or a cake?” “Either way, don’t fight him.” Bill leaned closer. “Where are the presents?” “On a table by the conservatory. We admire them, offer to move them somewhere safe, then wheel the whole table into the van.” “That’s your plan? Steal the table?” “Tables have wheels. Sacks don’t.” “Sacks have mouths.” “So do you, and look how much trouble that causes.” Bill considered this. “What if someone asks why we’re taking the table?” “We say the presents need to be weighed.” “Weighed?” “For the birthday quiz. Heaviest present wins.” “That sounds plausible.” “It sounds insane, which is why you must say it confidently.” Molly produced two badges. Bill’s read PROFESSOR GIGGLES. Hers read SHARON. “Why are you Sharon?” “Sharon handles logistics.” “What does Professor Giggles handle?” “Standing still and not improvising.” Bill tucked the badge into his pocket. “And the rabbit?” “Decoy.” “From what?” “Your face.” A delivery van rumbled past. Molly checked her watch. A roll of wrapping paper lay beside the invitation, covered in cartoon ducks. Someone had given the dinosaur a moustache. “Cute,” Bill said. “Don’t get attached.” “I wasn’t.” “You sighed at the wrapping paper.” “It’s nice paper.” “It has ducks on it.” “Ducks can be nice.” “Focus,” Molly said. “I am focused. I’m focused on how much I dislike planning with you.” “That’s not focus.” “One more thing,” she said. “No grabbing cake, no releasing balloons, and absolutely no getting into the bouncy castle.” “That was one time.” “You knocked over a vicar.” “He bounced into me.” “He was outside the castle.” Bill opened the van door. Inside lay the rabbit, a folding table, and an enormous sack labelled LAUNDRY. Molly stared at the sack. “What happened to using the table?” “Backup.” “Why does the laundry sack have eyeholes?” “Backup backup.” She sighed and climbed into the passenger seat. “Fine. But when this goes wrong, I’m Sharon, you’re Professor Giggles, and neither of us knows the owner of the rabbit.” Bill started the engine. “Agreed. Though technically, the rabbit is Professor Giggles.” Molly closed her eyes. “Drive, Bill.” “Right. Next stop, untold riches.” “They’re six, Bill. We’re stealing bubble mixture and a dinosaur that roars when you squeeze its bottom.” Bill grinned. “Still counts as a score.” “Only if you don’t squeeze it during the getaway.” The buckle began to play.
created_at
"2026-10-27T10:48:57.122Z"
10/27/2026, 10:48:57 AM
model
"moonshotai/kimi-k3.1-pro-20261023"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1650
moderation_latency
(null)
generation_time
178516
tokens_prompt
75
tokens_completion
6152
native_tokens_prompt
146
native_tokens_completion
6133
native_tokens_completion_images
(null)
native_tokens_reasoning
5326
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
0.061622
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.22.1; linux; x64))"
http_referer
(null)
request_id
"req-1793098137-ftq5eDvhg9DHH9iojYOS"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1793098137-LEyieG23ROjEjoUBiR3C"
upstream_id
"chatcmpl-6ae08199cd8d6358dffa24fd"
provider_responses
0
endpoint_id
"a3fafaac-f097-4ef1-86b3-842854dad5c6"
id
"chatcmpl-6ae08199cd8d6358dffa24fd"
is_byok
false
latency
1650
model_permaslug
"moonshotai/kimi-k3.1-pro-20261023"
provider_name
"Moonshot AI"
status
200
total_cost
0.061622
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
72.98%
Dialogue to Total Word Ratio
Ratio: 72.51%, Deviation: 2.51%
neededClean
false
wordsTotal
502
wordsDialogue
364
86.4896%