NC Bench
Overview
About
Tests
Models
Model
MoonshotAI: Kimi K2.5
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2026-02-08-01KGYZCGP2FR02BQY5114JHYFW
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 climbing harness beneath the pastel unicorn costume while Bill studied satellite imagery of the McAllister backyard on his burner phone. The bouncy castle loomed like an inflatable fortress, casting long shadows over the gift table where forty-seven wrapped boxes awaited their liberation. Through the kitchen window, they watched seven-year-olds assaulting a papier-mâché donkey with disturbing enthusiasm and aluminum baseball bats. "We're really doing this?" Bill whispered, sweat beading beneath his clown wig. "Quiet. Target's three feet from the door. Move fast." "Got it. Stay low." "And don't trip." Bill nodded, his squeaky oversized shoes betraying their position behind the hydrangea bushes. Inside, the magician had begun his finale, distracting the horde of sugar-crazed children with a velvet top hat and gestures. When the white dove flew out in a flurry of wings, they moved. Slipping through the unlocked door, they grabbed their empty duffel bags and began shoveling in LEGO sets and Barbies with practiced efficiency. The golden retriever wearing a party hat merely watched, tail wagging, as two grown adults in ridiculous costumes fled across the lawn clutching booty. They vaulted just as the birthday boy opened his present—an empty box filled with regret and a note that read: "Better luck next year, kid."
created_at
"2026-02-08T15:58:05.892678+00:00"
Sunday, February 8th, 2026 at 3:58:05 PM GMT+00:00
model
"moonshotai/kimi-k2.5-0127"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
783
moderation_latency
(null)
generation_time
210528
tokens_prompt
61
tokens_completion
10631
native_tokens_prompt
68
native_tokens_completion
10712
native_tokens_completion_images
(null)
native_tokens_reasoning
10353
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
0.0321428
router
(null)
provider_responses
0
id
"chatcmpl-6988b1bb1558f525c825dafb"
status
200
is_byok
false
latency
783
endpoint_id
"49762299-66fd-4514-b0ee-c9e11e231e3b"
provider_name
"Moonshot AI"
model_permaslug
"moonshotai/kimi-k2.5-0127"
api_type
"completions"
id
"gen-1770566075-UKl9JRtGxNALVe6cQP31"
upstream_id
"chatcmpl-6988b1bb1558f525c825dafb"
total_cost
0.0321428
cache_discount
0.000034
upstream_inference_cost
0
provider_name
"Moonshot AI"
Evaluation details
Result
Evaluator
Details
Meta Data
68.1022%
Matches word count
n/a
neededClean
false
words
214
99.9199%
Dialogue to Total Word Ratio
Ratio: 11.68%, Deviation: 1.68%
neededClean
false
wordsTotal
214
wordsDialogue
25
84.0111%