NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD7TB2S6ZP2B0WN1Z8AG3HN
Run Details
Model:
MoonshotAI: Kimi K3 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
13.1s
Cost:
$0.004769
Provider:
Moonshot AI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.16%
Dialogue to Total Word Ratio
(details)
99.5772%
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 spread a crayon drawing of a bounce house across the dashboard. "Okay, Molly. The presents are here, next to the cake table." "Bill, that's a child's drawing." "It's a blueprint. Little Timmy made it. He also drew a dragon on the roof, which I'm choosing to ignore." "We're stealing presents from a seven-year-old's birthday party." "We're redistributing joy, Molly. To ourselves." "And the clown?" "Distraction. I hired him. Twenty bucks, he juggles, all eyes on him." "You hired a clown with our getaway money?" "He was very persuasive. He had a horn." Molly sighed. "What's our cover story?" "You're Aunt Deborah. I'm Uncle Gerald. We've been skiing." "In July." "Swiss skiing. Very exclusive." "And when someone asks little Timmy who we are?" "He'll say Aunt Deborah and Uncle Gerald. Kids are terrible witnesses, Molly. It's science." "It is not science." "Fine. Backup plan: we grab the presents and hide in the bounce house." "The bounce house made of air and lies?" "Nobody suspects the bounce house." "I suspect the bounce house." "Then we're already ahead of the game. Masks on?" "These are paper plates with eye holes." "Timmy made those too. Solid kid. Now, go steal some joy."
created_at
"2026-07-25T18:15:22.464Z"
7/25/2026, 6:15:22 PM
model
"moonshotai/kimi-k3-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2164
moderation_latency
(null)
generation_time
12862
tokens_prompt
75
tokens_completion
324
native_tokens_prompt
147
native_tokens_completion
315
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
0.0047691
router
(null)
provider_responses
0
endpoint_id
"650c9b12-7b6d-444d-8d92-df8daef84d7a"
id
"chatcmpl-6a64fd2641ab1022070b4681"
is_byok
false
latency
2164
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-1785003322-51Qh3vU0XJHtGyzWGXLa"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785003322-5OG9EkyvLXL5tQUULuZJ"
upstream_id
"chatcmpl-6a64fd2641ab1022070b4681"
total_cost
0.0047691
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
100.00%
Matches word count
n/a
neededClean
false
words
199
99.16%
Dialogue to Total Word Ratio
Ratio: 93.03%, Deviation: 3.03%
neededClean
false
wordsTotal
201
wordsDialogue
187
99.5772%