NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD583TFY3JXFGE8PRY4XWJV
Run Details
Model:
MoonshotAI: Kimi K3 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
15.5s
Cost:
$0.005519
Provider:
Moonshot AI
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
58.29%
Dialogue to Total Word Ratio
(details)
75.9688%
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 doing this?" Bill whispered, crouched behind a hedge shaped like a giraffe. "Shh. The clown's on break. That's our window," Molly said, unrolling a hand-drawn map covered in crayon. "I bribed the birthday girl's brother for intel. Cost me three fruit snacks." "Worth every snack. Where's the loot?" "Pile's by the bouncy castle. Guarded by a woman named Debra who has not blinked once since we got here." "Debra's a problem." "Debra's a obstacle, Bill. Problems can be solved. Obstacles we go around. Or through. I brought a whoopee cushion for diversion purposes." "That's your plan? A whoopee cushion?" "It's a classic for a reason. You grab the presents, I create chaos, we rendezvous at the minivan." "What if a kid sees us?" "Then you freeze. They can't see you if you don't move. That's science." "That's dinosaurs, Molly. That's dinosaur science." "Same thing. Now, masks on." She pulled a paper plate with eye holes over her face. It had a smiley sun drawn on it. "Why does mine say 'World's Best Grandma'?" "It was that or a Christmas one. Timing was tight." "I hate this job." "You love this job. On three. One, two—" "Wait, is that a piñata? Do we take the piñata?" "Bill. Focus."
created_at
"2026-07-25T17:30:28.055Z"
7/25/2026, 5:30:28 PM
model
"moonshotai/kimi-k3-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2932
moderation_latency
(null)
generation_time
15400
tokens_prompt
75
tokens_completion
350
native_tokens_prompt
147
native_tokens_completion
365
native_tokens_completion_images
(null)
native_tokens_reasoning
31
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
0.0055191
router
(null)
provider_responses
0
endpoint_id
"650c9b12-7b6d-444d-8d92-df8daef84d7a"
id
"chatcmpl-6a64f2a465f53349321aeae3"
is_byok
false
latency
2932
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-1785000628-Gjg5go7OKoBcYqQZugMi"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785000628-nekz6GXHukSkXIoYWiMB"
upstream_id
"chatcmpl-6a64f2a465f53349321aeae3"
total_cost
0.0055191
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
93.65%
Matches word count
n/a
neededClean
false
words
209
58.29%
Dialogue to Total Word Ratio
Ratio: 81.43%, Deviation: 8.57%
neededClean
false
wordsTotal
210
wordsDialogue
171
75.9688%