NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD536C474ZFPP5FDBWNB8XJ
Run Details
Model:
MoonshotAI: Kimi K3 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 57s
Cost:
$0.035894
Provider:
Moonshot AI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
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 crouched behind the hedge across from number seven, watching paper hats bob through the window like ducks at a shooting gallery. Bill lay beside her in a stolen waiter jacket, black socks up to his knees, eyes shining with the solemn greed of a raccoon near cake. Inside, twenty children screamed at a magician pulling ribbons from a volunteer ear. On the lawn sat the bounty: bicycles wrapped in silver, a dragon piñata fat with candy, gift bags stacked like a rainbow bank vault. Molly whispered, “We enter as balloon artists, not burglars.” Bill said, “Fine, but I refuse tiny shoes.” Molly added, “Wear sandals, look festive, please.” Bill muttered, “Absolutely not.” The plan was elegant in the way gravy is elegant. At three, the clown would faint from gin. Bill would wheel in a cake hollow enough for treasure. Molly would charm the parents with business cards naming them Sir Splat and Lady Noodle. Nobody suspects whimsy. Then came the flaw: the birthday girl spotted Bill’s mustache sliding south and pointed with terrible accuracy. Molly smiled at every mother present while privately promoting the fire escape from exit to sweetheart and christening the bouncy castle their getaway coach.
created_at
"2026-07-25T17:28:24.89Z"
7/25/2026, 5:28:24 PM
model
"moonshotai/kimi-k3-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2493
moderation_latency
(null)
generation_time
79249
tokens_prompt
75
tokens_completion
2464
native_tokens_prompt
147
native_tokens_completion
2390
native_tokens_completion_images
(null)
native_tokens_reasoning
2115
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
0.0358941
router
(null)
provider_responses
0
endpoint_id
"650c9b12-7b6d-444d-8d92-df8daef84d7a"
id
"chatcmpl-6a64f23a23b4992063bac8cc"
is_byok
false
latency
2493
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-1785000504-SY0k3EopJQfmCqxFTMZn"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785000504-ECwyjksjF31ToBEc8qA6"
upstream_id
"chatcmpl-6a64f23a23b4992063bac8cc"
total_cost
0.0358941
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
200
100.00%
Dialogue to Total Word Ratio
Ratio: 10.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
20
100.0000%