NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD5NEVXYZ4AC7D2HT45WNKK
Run Details
Model:
MoonshotAI: Kimi K3 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
14.9s
Cost:
$0.005474
Provider:
Moonshot AI
Evaluation summary
Score
Evaluator
Details Link
81.27%
Matches word count
(details)
94.15%
Dialogue to Total Word Ratio
(details)
87.7134%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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-drawn map across the dashboard. "Okay. Party starts at two. Clown arrives at two-fifteen. We go in at two-twenty." "Why two-twenty?" Bill asked. "Because that's when the clown does the balloon animals, and every adult in that house will be filming him on their phones." "You're a genius." "I'm aware. Now, disguises. You're the magician's assistant." "I'm not wearing a leotard." "You're wearing the leotard, Bill. It's the only thing that says 'children's entertainer' and not 'man who collects debt.'" "What if a kid asks me to do a trick?" "Pull a quarter from behind their ear." "I don't know how to do that." "Then learn! We have three days! What can you do?" "I can juggle." "Since when?" "Prison." "Of course. Fine, you juggle, I grab the presents, we stuff them in the piñata, and we walk out carrying the piñata like it's ours." "Isn't that suspicious? Two grown adults leaving a party with a donkey full of gifts?" "Bill, it's a party for a six-year-old. By three o'clock, every parent there will be too exhausted to care what we take." "What about the cake?" "We're stealing presents, not cake." "Seems like a waste." "Focus, Bill." "Sorry. Do I get a wand?" "Yes, Bill. You get a wand."
created_at
"2026-07-25T17:37:45.349Z"
7/25/2026, 5:37:45 PM
model
"moonshotai/kimi-k3-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2310
moderation_latency
(null)
generation_time
14813
tokens_prompt
75
tokens_completion
345
native_tokens_prompt
147
native_tokens_completion
362
native_tokens_completion_images
(null)
native_tokens_reasoning
25
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
0.0054741
router
(null)
provider_responses
0
endpoint_id
"650c9b12-7b6d-444d-8d92-df8daef84d7a"
id
"chatcmpl-6a64f45541ab1022070b3f48"
is_byok
false
latency
2310
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-1785001065-Y39FG1gaZ0asmLKT3jiP"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785001065-R9thjKVPxnhsgGAcngA2"
upstream_id
"chatcmpl-6a64f45541ab1022070b3f48"
total_cost
0.0054741
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
81.27%
Matches word count
n/a
neededClean
false
words
212
94.15%
Dialogue to Total Word Ratio
Ratio: 94.95%, Deviation: 4.95%
neededClean
false
wordsTotal
218
wordsDialogue
207
87.7134%