NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD5TQX61ZSEYF0TJQKXJSGW
Run Details
Model:
MoonshotAI: Kimi K3 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
19.0s
Cost:
$0.006981
Provider:
Moonshot AI
Evaluation summary
Score
Evaluator
Details Link
75.16%
Matches word count
(details)
97.31%
Dialogue to Total Word Ratio
(details)
86.2343%
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
"We're really robbing a birthday party?" Bill whispered, crouched behind a shrub shaped like a giraffe. "Not robbing," Molly said. "Redistributing." "There's a bouncy castle." "Bill. Focus. The clown leaves at four, the magician at four-thirty, and the presents are unattended during cake." "What about the kids?" "Seven years old, hopped up on frosting. They're basically security guards with no object permanence." "And the piƱata?" "Decoy. Full of raisins. Nobody wants that." Bill squinted at the window. "That's a lot of wrapped boxes." "That's a lot of unwrapped profit. Toys appreciate, Bill. Limited editions. A mint-condition Robo-Saurus goes for two hundred easy." "What's the code word if parents show up?" "Balloons." "That's not a code word, that's just a word." "It's a party, Bill. Everything's balloons. We'll blend in. I brought a hat." Molly produced a cone-shaped hat with an elastic string. "You're wearing that?" "We're guests now. Guests can't steal. It's etiquette." "What if a kid catches us?" "We tell them we're the present fairies." "Is that a thing?" "It is tonight. Now stop sweating, you look guilty." "I am guilty." "Not until four-fifteen, you're not."
created_at
"2026-07-25T17:40:38.45Z"
7/25/2026, 5:40:38 PM
model
"moonshotai/kimi-k3-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1999
moderation_latency
(null)
generation_time
18874
tokens_prompt
75
tokens_completion
465
native_tokens_prompt
147
native_tokens_completion
436
native_tokens_completion_images
(null)
native_tokens_reasoning
131
native_tokens_cached
0
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
0.006981
router
(null)
provider_responses
0
endpoint_id
"650c9b12-7b6d-444d-8d92-df8daef84d7a"
id
"chatcmpl-6a64f50291cc633c33dc9416"
is_byok
false
latency
1999
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-1785001238-gK7BCm4VTp2tHLG7Yb1E"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785001238-HCG2pGNXVvaMo2lZWIFx"
upstream_id
"chatcmpl-6a64f50291cc633c33dc9416"
total_cost
0.006981
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Moonshot AI"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
75.16%
Matches word count
n/a
neededClean
false
words
187
97.31%
Dialogue to Total Word Ratio
Ratio: 85.94%, Deviation: 4.06%
neededClean
false
wordsTotal
192
wordsDialogue
165
86.2343%