NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD6QG1Y82KMG0KVR02HAEW5
Run Details
Model:
MoonshotAI: Kimi K3 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
12.5s
Cost:
$0.004994
Provider:
Moonshot AI
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
97.09%
Dialogue to Total Word Ratio
(details)
98.5358%
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 unfolded the blueprint across the dashboard of their stolen ice cream truck. "Okay, Bill, the Henderson kid's party. Saturday, two o'clock. We go in as clowns." "Why do I have to be the sad clown?" "Because you cried at the last job." "It was a piƱata funeral, Molly. I have feelings." "Focus. Twenty presents, one bouncy castle, thirty sugared-up children between us and the door." Bill squinted at the diagram. "What's this squiggle?" "That's a magician." "A magician? You didn't say there'd be a magician!" "He pulls rabbits out of hats, Bill, not Uzis." "I don't trust a man with an endless supply of doves. Where does he keep them? Why does nobody ask?" Molly pinched the bridge of her nose. "Plan B, then. You distract the magician, I grab the gift table." "Distract him how?" "Ask about the doves." "Oh, I'll ask about the doves." Bill cracked his knuckles. "What if the presents are all clothes? Last time I risked my neck for a sweater vest." "A seven-year-old's birthday, Bill. Nobody gives a kid a sweater vest." "My Aunt Linda did." "Your Aunt Linda's a monster. Now put on the wig." "Which wig?" "The one that doesn't smell like alibis."
created_at
"2026-07-25T17:56:20.677Z"
7/25/2026, 5:56:20 PM
model
"moonshotai/kimi-k3-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2402
moderation_latency
(null)
generation_time
12434
tokens_prompt
75
tokens_completion
317
native_tokens_prompt
147
native_tokens_completion
330
native_tokens_completion_images
(null)
native_tokens_reasoning
17
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
0.0049941
router
(null)
provider_responses
0
endpoint_id
"650c9b12-7b6d-444d-8d92-df8daef84d7a"
id
"chatcmpl-6a64f8c624e293d5e4a0eeab"
is_byok
false
latency
2402
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-1785002180-DyLzPkenhr4bPVfzTI77"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785002180-Xaid4SFfOeYjCut5nUNk"
upstream_id
"chatcmpl-6a64f8c624e293d5e4a0eeab"
total_cost
0.0049941
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
99.98%
Matches word count
n/a
neededClean
false
words
202
97.09%
Dialogue to Total Word Ratio
Ratio: 85.85%, Deviation: 4.15%
neededClean
false
wordsTotal
205
wordsDialogue
176
98.5358%