NC Bench
Overview
About
Tests
Models
Model
MoonshotAI: Kimi K2.5
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2026-02-08-01KGZ07A3QDY6T05V36156R32H
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
"You're suggesting we tunnel through the ball pit?" Bill adjusted his ski mask. "Obviously. The presents are guarded by a clown with a squeaky nose. We enter during the piƱata chaos." "Why not just pose as parents?" "You're forty and allergic to glitter. The 'Cool Uncle' cover is thinner than the ice cream cake." Bill frowned at the map. "But tunneling?" "Standard procedure. Dig under the table, grab the Xbox, exit through the craft station." "What about the six-year-olds?" "Juice boxes laced with extra sugar. Hyperactivity is our distraction." "If the clown catches us?" "Acoustic warfare." Molly held up a whoopee cushion. "One squeeze, he trips over his shoes." "Brilliant." "Now suit up. Party starts at two, and I want that Lego set." "Should we bring gifts to blend in?" "We're stealing them, Bill, not exchanging them." "Right. Old habits." "Focus. This is the big leagues. Disney princesses and limited edition cards." "Let's break some hearts." "Gently. It's a children's party, not a bank." "Still counts as a heist." "It counts as larceny with cake." "Pink frosting on the cake?" Bill scratched his chin. "Red velvet. We're monsters, not animals." "Bring the big bag." "Obviously. And Bill? Try not to cry when they sing Happy Birthday. It's unprofessional."
created_at
"2026-02-08T16:10:53.273644+00:00"
Sunday, February 8th, 2026 at 4:10:53 PM GMT+00:00
model
"moonshotai/kimi-k2.5-0127"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
772
moderation_latency
(null)
generation_time
99650
tokens_prompt
61
tokens_completion
5260
native_tokens_prompt
68
native_tokens_completion
5301
native_tokens_completion_images
(null)
native_tokens_reasoning
5314
native_tokens_cached
68
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
0.0159098
router
(null)
provider_responses
0
id
"chatcmpl-6988b52942b2637122696aa3"
status
200
is_byok
false
latency
772
endpoint_id
"49762299-66fd-4514-b0ee-c9e11e231e3b"
provider_name
"Moonshot AI"
model_permaslug
"moonshotai/kimi-k2.5-0127"
api_type
"completions"
id
"gen-1770566953-0ChNJd0FPA0Xazs6t3V9"
upstream_id
"chatcmpl-6988b52942b2637122696aa3"
total_cost
0.0159098
cache_discount
0.000034
upstream_inference_cost
0
provider_name
"Moonshot AI"
Evaluation details
Result
Evaluator
Details
Meta Data
90.4837%
Matches word count
n/a
neededClean
false
words
210
99.9995%
Dialogue to Total Word Ratio
Ratio: 90.48%, Deviation: 0.48%
neededClean
false
wordsTotal
210
wordsDialogue
190
95.2416%