NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD6TKZ5BW2AFKKSRR80AZ9H
Run Details
Model:
MoonshotAI: Kimi K3 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
15.0s
Cost:
$0.005714
Provider:
Moonshot AI
Evaluation summary
Score
Evaluator
Details Link
14.30%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
7.1507%
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
Molly spread the crayon drawing across the dashboard. "This is the blueprint. Tommy's mom drew it for the invitation." Bill squinted. "That's a bouncy castle." "It's a tactical entry point." "It's got a slide." "That's how we escape." Molly tapped the page. "Saturday. Two o'clock. Twenty kids, thirty presents, one piñata full of premium chocolate." "How do you know the chocolate's premium?" "I have sources." Bill rubbed his chin. "What's our cover? We can't exactly walk into a seven-year-old's birthday." Molly pulled two rainbow wigs from the glove compartment. "We're clowns." "I'm not wearing the wig." "You're wearing the wig, Bill." "Why do I get the pink one?" "Because last time you wore red, a dog attacked you." Bill sighed and took the wig. "Fine. But what's the plan once we're in?" "Simple. You do balloon animals to distract the parents. I load the presents into the magic trunk." "The magic trunk is a trash can." "It's a magician's trash can. There's a difference." Bill stared at her. "Molly, we're stealing from children." "We're relocating unwrapped inventory. The kids won't even notice. They'll be hyped up on cake." "What if Tommy cries?" Molly paused. "We leave him the piñata. We're not monsters." "Very generous." "Get in costume, Bill. We steal at two." "Can I at least keep one balloon animal?" "One."
created_at
"2026-07-25T17:58:02.987Z"
7/25/2026, 5:58:02 PM
model
"moonshotai/kimi-k3-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2180
moderation_latency
(null)
generation_time
14976
tokens_prompt
75
tokens_completion
397
native_tokens_prompt
147
native_tokens_completion
378
native_tokens_completion_images
(null)
native_tokens_reasoning
41
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
0.0057141
router
(null)
provider_responses
0
endpoint_id
"650c9b12-7b6d-444d-8d92-df8daef84d7a"
id
"chatcmpl-6a64f9168b0721cfd7eea6a5"
is_byok
false
latency
2180
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-1785002283-2jdlQ1xjVqziNc3ok7tg"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785002283-nZNC1JDXsd4RSwktBjAr"
upstream_id
"chatcmpl-6a64f9168b0721cfd7eea6a5"
total_cost
0.0057141
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
14.30%
Matches word count
n/a
neededClean
false
words
221
0.00%
Dialogue to Total Word Ratio
Ratio: 82.51%, Deviation: 32.51%
neededClean
false
wordsTotal
223
wordsDialogue
184
7.1507%