NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD7DTHBQMK7W765AB5486YT
Run Details
Model:
MoonshotAI: Kimi K3 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
14.0s
Cost:
$0.005009
Provider:
Moonshot AI
Evaluation summary
Score
Evaluator
Details Link
81.27%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
90.6363%
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 spread the hand-drawn map across Bill's dashboard. "Okay. Party starts at two. The clown arrives at two-fifteen." "A clown?" Bill whispered. "Nobody said anything about a clown." "Focus. The presents get piled on the gift table by the patio. That's our window." "And the clown?" "The clown is a wildcard, Bill. Every job has a wildcard." Bill squinted at the map. "Is that a crayon drawing of a bouncy castle?" "It's called casing the target, and yes, Timmy's birthday party has a bouncy castle. Which is good. Bouncy castles mean distracted parents." "What if the kids see us?" "They're six years old, Bill. We tell them we're gift inspectors." "That's a thing?" "It's a thing now. You wear the badge, you carry the clipboard, you look official." Molly tapped the map. "We grab the presents, load them in the van, and we're gone before the cake comes out." "Can we stay for cake?" "We are not staying for cake." "Chocolate, though. I heard the mom say chocolate." Molly sighed. "Fine. One slice. But if that clown looks at me funny, we're leaving, presents or no presents." "Deal. Wait—why do I have to wear the badge?" "Because you have the face of a gift inspector." "That's not a compliment, is it?"
created_at
"2026-07-25T18:08:32.306Z"
7/25/2026, 6:08:32 PM
model
"moonshotai/kimi-k3-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2281
moderation_latency
(null)
generation_time
13958
tokens_prompt
75
tokens_completion
330
native_tokens_prompt
147
native_tokens_completion
331
native_tokens_completion_images
(null)
native_tokens_reasoning
15
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
0.0050091
router
(null)
provider_responses
0
endpoint_id
"650c9b12-7b6d-444d-8d92-df8daef84d7a"
id
"chatcmpl-6a64fb8b62d867bab807e23e"
is_byok
false
latency
2281
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-1785002912-XsX5gieM7enUhR44oN8G"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785002912-LzKdEkGSS57tqChCb7KO"
upstream_id
"chatcmpl-6a64fb8b62d867bab807e23e"
total_cost
0.0050091
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
81.27%
Matches word count
n/a
neededClean
false
words
212
100.00%
Dialogue to Total Word Ratio
Ratio: 89.72%, Deviation: 0.28%
neededClean
false
wordsTotal
214
wordsDialogue
192
90.6363%