NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD675CC64ZBN14VZPG49FKP
Run Details
Model:
MoonshotAI: Kimi K3 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
46.7s
Cost:
$0.021104
Provider:
Moonshot AI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9995%
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
Outside the bakery window Molly drew a map on a napkin while Bill buttered a roll like it owed him money. Across the street balloons bobbed over the fence of number six where tiny shoes squeaked toward treasure. Molly tapped the napkin with one dramatic finger. "We tiptoe in at cake time, grab the shiny boxes, and leave before the clown notices." Bill nodded so hard his hat fell off. "Brilliant, except clowns notice everything, and my knees squeak when I steal from toddlers." A magician across the room produced a rabbit from a cake and both thieves gasped with professional respect. "Wear rubber soles, bring the duck wagon, and remember wrapping paper is louder than guilt." "Fine, but if a balloon pops, I am hiding inside the gift table like a coward." Then the birthday song began off key and Molly folded the map into a swan. "No hiding, no crying, no tasting frosting unless it helps morale." Bill saluted the swan. "Morale loves frosting, and so do I, captain." "Then we are criminals with snacks, not monsters, understood?" "Understood, mostly." They looked very sneaky and completely obvious simultaneously. "Good. Bill, stop winking at the piƱata." "Old habits."
created_at
"2026-07-25T17:47:25.459Z"
7/25/2026, 5:47:25 PM
model
"moonshotai/kimi-k3-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2296
moderation_latency
(null)
generation_time
46568
tokens_prompt
75
tokens_completion
1439
native_tokens_prompt
147
native_tokens_completion
1404
native_tokens_completion_images
(null)
native_tokens_reasoning
1124
native_tokens_cached
147
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
0.0211041
router
(null)
provider_responses
0
endpoint_id
"650c9b12-7b6d-444d-8d92-df8daef84d7a"
id
"chatcmpl-6a64f6ae81eb13cded511145"
is_byok
false
latency
2296
model_permaslug
"moonshotai/kimi-k3-20260715"
provider_name
"Moonshot AI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1785001645-p3wTylS2r7w6yQeeaHq9"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785001645-5uCNDwUErvQyVPKJCalE"
upstream_id
"chatcmpl-6a64f6ae81eb13cded511145"
total_cost
0.0211041
cache_discount
0.0003969
upstream_inference_cost
0
provider_name
"Moonshot AI"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
199
100.00%
Dialogue to Total Word Ratio
Ratio: 50.25%, Deviation: 0.25%
neededClean
false
wordsTotal
199
wordsDialogue
100
99.9995%