NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD6V6SC9M3Y5RP5QFR1CGM1
Run Details
Model:
MoonshotAI: Kimi K3 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
15.8s
Cost:
$0.004949
Provider:
Moonshot AI
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
67.7502%
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
"Bill, explain the plan again, slowly, because I think I misheard the part where you're dressed as a clown." "I'm Buttons. Buttons the Magnificent. You said we needed cover." "I said we needed A cover. Like a catering van. Not balloon animals, Bill." "The van was forty quid to rent. This costume was twelve." "Fine. Fine! So you're Buttons. I'm what, exactly?" "My lovely assistant." "At a five-year-old's birthday party, you're going to sneak thirty presents past thirty children who have the observational skills of tiny drunk detectives." "Kids are idiots, Molly." "Kids are NEVER idiots about presents, Bill. Presents are their whole religion." "Then we move during the cake. All eyes on the cake." "That's actually not bad." "Thank you." "And the escape?" "Balloon release. Chaos. We walk out the back with the loot sack." "You cannot outrun a room of sugared-up children, Bill. They travel in packs. I've seen it. It's like velociraptors." "It's one street, Molly. In and out." "And if a kid grabs the sack?" "I honk the nose. It's disorienting." "...Why do I work with you?" "Because last time YOU suggested we rob a toy shop dressed as elves." "In AUGUST, Bill. It was thematically bold." "Get in the van, Buttons."
created_at
"2026-07-25T17:58:22.261Z"
7/25/2026, 5:58:22 PM
model
"moonshotai/kimi-k3-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2678
moderation_latency
(null)
generation_time
15004
tokens_prompt
75
tokens_completion
334
native_tokens_prompt
147
native_tokens_completion
327
native_tokens_completion_images
(null)
native_tokens_reasoning
12
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
0.0049491
router
(null)
provider_responses
0
endpoint_id
"650c9b12-7b6d-444d-8d92-df8daef84d7a"
id
"chatcmpl-6a64f9289e13a8d48a52a65b"
is_byok
false
latency
2678
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-1785002302-ULIQ6Bnw9z83kKXoGwzH"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785002302-9d2v0Vy39wwoKPenfMUz"
upstream_id
"chatcmpl-6a64f9289e13a8d48a52a65b"
total_cost
0.0049491
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
98.71%
Matches word count
n/a
neededClean
false
words
206
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
209
wordsDialogue
209
67.7502%