NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-08-01KGYX6TP2J7ZRNP4MW7YAZA1H
Run Details
Model:
MoonshotAI: Kimi K2.5
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
3m 57s
Cost:
$0.027273
Provider:
Venice
Evaluation summary
Score
Evaluator
Details Link
60.28%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
80.1364%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 adjusted her ski mask while her coffee grew cold in the cupholder. Outside the van, deflated balloon animals littered the suburban sidewalk like casualties of war. A bouncy castle dominated the front lawn, its primary colors screaming Targets Acquired. Bill juggled three lockpicks, nodding toward the bungalow with its rainbow banners. His reflection revealed a man who had lost all shame. "You're sure about this?" Molly asked. "The invitation says age five." "Positive. Little Timmy scored a PS5 and three hundred in LEGO." "Security?" "Clowns. One magician with a fake mustache." Molly frowned at the bouncy castle blocking their approach. The vinyl structure cast long shadows across the grass. "Distraction plan?" Bill tapped the glitter-covered piƱata in his lap. It rattled with counterfeit candy. "When I signal, crawl through the ball pit. I'll deflate the castle." "That's our exit!" "Backup plan B. We strike during musical chairs. Maximum chaos." "What about the kids?" "Candy. Bribery beats burglary." "I went to MIT for this," Molly muttered, loading gift bags into her tactical vest. "You studied algorithms," Bill said, checking his watch. "This is volume times value divided by toddler attention spans." "Glitter on this suit means you pay for dry cleaning." "Deal. Now look innocent." "I am. I'm stealing a Lamborghini wrapped in Spider-Man paper."
created_at
"2026-02-08T15:20:28.848079+00:00"
2/8/2026, 3:20:28 PM
model
"moonshotai/kimi-k2.5-0127"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1936
moderation_latency
(null)
generation_time
236482
tokens_prompt
61
tokens_completion
7284
native_tokens_prompt
87
native_tokens_completion
7259
native_tokens_completion_images
(null)
native_tokens_reasoning
7007
native_tokens_cached
21
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.027273375
router
(null)
provider_responses
0
id
"efb07a0b28eb4cdbaeb231c55e5c9e4b"
status
200
is_byok
false
latency
1935
endpoint_id
"c884a526-d529-4263-bd90-a58ea25e99d1"
provider_name
"Venice"
model_permaslug
"moonshotai/kimi-k2.5-0127"
api_type
"completions"
id
"gen-1770563791-9dzGcp5lmfqj7sxPkOsr"
upstream_id
"efb07a0b28eb4cdbaeb231c55e5c9e4b"
total_cost
0.027273375
cache_discount
0.000013125
upstream_inference_cost
0
provider_name
"Venice"
Evaluation details
Result
Evaluator
Details
Meta Data
60.28%
Matches word count
n/a
neededClean
false
words
215
100.00%
Dialogue to Total Word Ratio
Ratio: 49.31%, Deviation: 0.69%
neededClean
false
wordsTotal
217
wordsDialogue
107
80.1364%