NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD5692D4ZHXTD9AQ0RJGY3W
Run Details
Model:
MoonshotAI: Kimi K3 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
43.9s
Cost:
$0.020999
Provider:
Moonshot AI
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
39.66%
Dialogue to Total Word Ratio
(details)
69.7004%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 blueprint across the dashboard while Bill adjusted his false mustache, which had come from a cereal box and smelled faintly of marshmallow. Outside, the Hendersons’ yard glittered with streamers, a bounce house sighing like a tired dragon, and twenty small humans hyped on sugar. “The clown is the guard,” Molly whispered. Bill peered through binoculars made from toilet tubes. “I brought balloons.” “For camouflage?” “For moral support.” She pinched the bridge of her nose. Their disguises hung in the back seat: two giant teddy-bear costumes with eyeholes cut crooked, because Bill insisted symmetry was suspicious. The plan was elegant in the way a falling piano is elegant. Enter during musical chairs. Blend with the gift table. Redirect the piñata mob toward the fence. Load every wrapped box into the ice-cream truck they had borrowed from Bill’s cousin, who thought they were finally going straight. “We leave at naptime,” Molly said. “Cake first, presents second,” Bill replied, already drooling. A kazoo blared. The clown turned slowly, suspicious, balloon sword raised. Molly slid the transmission into drive. Bill saluted with a juice box. Crime, they agreed, was mostly timing, comfortable shoes, and never trusting a man in a giraffe suit ever again.
created_at
"2026-07-25T17:29:27.896Z"
7/25/2026, 5:29:27 PM
model
"moonshotai/kimi-k3-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2383
moderation_latency
(null)
generation_time
43824
tokens_prompt
75
tokens_completion
1460
native_tokens_prompt
147
native_tokens_completion
1397
native_tokens_completion_images
(null)
native_tokens_reasoning
1096
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
0.0209991
router
(null)
provider_responses
0
endpoint_id
"650c9b12-7b6d-444d-8d92-df8daef84d7a"
id
"chatcmpl-6a64f279689654d454e9fd17"
is_byok
false
latency
2383
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-1785000567-8zyPoHcFhXmPOrbwS6aH"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785000567-XNjI9Vd4e5MnyatnjSEg"
upstream_id
"chatcmpl-6a64f279689654d454e9fd17"
total_cost
0.0209991
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
99.74%
Matches word count
n/a
neededClean
false
words
204
39.66%
Dialogue to Total Word Ratio
Ratio: 19.81%, Deviation: 9.81%
neededClean
false
wordsTotal
207
wordsDialogue
41
69.7004%