NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD6BQFT5XN5CBTRGQAF3KYQ
Run Details
Model:
MoonshotAI: Kimi K3 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
13.4s
Cost:
$0.004664
Provider:
Moonshot AI
Evaluation summary
Score
Evaluator
Details Link
86.38%
Matches word count
(details)
97.67%
Dialogue to Total Word Ratio
(details)
92.0263%
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 crayon-scribbled map across Bill's dashboard. "The party's Saturday. Three o'clock. Hibiscus Drive." "You're telling me," Bill said, squinting, "that we're robbing a seven-year-old." "We're robbing forty seven-year-olds' worth of presents, Bill. Big difference." "I feel like it's actually worse." "The Henderson kid's getting a Nintendo. Do you know what a Nintendo goes for?" "What a Nintendo goes for is evidence. Cops love Nintendos." "Then we'll wear the clown costumes." Bill put his head on the steering wheel. "We are not wearing the clown costumes." "Nobody suspects the clowns, Bill. That's the whole point of clowns." "I suspect clowns. Everybody suspects clowns. Children cry at clowns." "Fine. Magicians." "Same thing with hats." "It's not the same—look, we go in, we do the balloon animals, and while they're singing happy birthday, we load the presents into the van." "You can't do balloon animals. Last time you made a dog and it looked like a crime scene." "It was abstract." "It was a warning, Molly." She rolled up the map. "Saturday. Three o'clock. Bring the good balloons." Bill sighed. "I'm bringing the bad balloons. That's all we deserve."
created_at
"2026-07-25T17:49:55.075Z"
7/25/2026, 5:49:55 PM
model
"moonshotai/kimi-k3-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2088
moderation_latency
(null)
generation_time
13353
tokens_prompt
75
tokens_completion
319
native_tokens_prompt
147
native_tokens_completion
308
native_tokens_completion_images
(null)
native_tokens_reasoning
14
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
0.0046641
router
(null)
provider_responses
0
endpoint_id
"650c9b12-7b6d-444d-8d92-df8daef84d7a"
id
"chatcmpl-6a64f730964c85e277242e31"
is_byok
false
latency
2088
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-1785001795-BBdfpBWddXQHBG6tmFlg"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785001795-fJ8LSB79q0Ik6AcQlvZg"
upstream_id
"chatcmpl-6a64f730964c85e277242e31"
total_cost
0.0046641
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
86.38%
Matches word count
n/a
neededClean
false
words
189
97.67%
Dialogue to Total Word Ratio
Ratio: 86.08%, Deviation: 3.92%
neededClean
false
wordsTotal
194
wordsDialogue
167
92.0263%