NC Bench
Overview
About
Tests
Models
Model
MoonshotAI: Kimi K2.5
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2026-02-08-01KGYZ6FAEYQ7BAFJXHCTTPN14
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, you're telling me we need to crack a bouncy castle?" Bill asked, tightening his ski mask. "It's not just a bouncy castle, Bill. It's a fortress with air vents and a ball pit moat," Molly said, unrolling crayon-blueprints across the steering wheel. "The target is inside the piñata." "The piñata? I thought we were grabbing Nintendo Switches and Legos." "We are. The birthday boy's parents put everything in the donkey to save on wrapping paper." Bill squinted. "Why's there a crying clown in the margin?" "That's you, Bill. That's your disguise." "I'm absolutely not dressing as a clown." "You have to. The code phrase is 'Who wants balloon animals?' Then we neutralize the magician." "Neutralize? He's six years old, Molly." "He's a competitive threat with a sippy cup. Plus he saw my face at the library during story hour." "What about the parents?" "Cake distraction. I spike the punch with sleeping pills—grape flavor, obviously." "Obviously." "Then we rappel from the treehouse, grab the donkey, and exfiltrate through the sandbox." "Do I at least get a squirting flower?" "Only if you don't cry when they pelt you with sticks." "This is literally the stupidest job we've ever done." "Stupid? Bill, we're talking thirty bucks in Target gift cards and possibly a Lego Death Star." "Fine. But I'm keeping the red nose."
created_at
"2026-02-08T15:53:07.013991+00:00"
Sunday, February 8th, 2026 at 3:53:07 PM GMT+00:00
model
"moonshotai/kimi-k2.5-0127"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
841
moderation_latency
(null)
generation_time
109392
tokens_prompt
61
tokens_completion
5451
native_tokens_prompt
68
native_tokens_completion
5421
native_tokens_completion_images
(null)
native_tokens_reasoning
5042
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
0.0162698
router
(null)
provider_responses
0
id
"chatcmpl-6988b0f50362885b09107267"
status
200
is_byok
false
latency
841
endpoint_id
"49762299-66fd-4514-b0ee-c9e11e231e3b"
provider_name
"Moonshot AI"
model_permaslug
"moonshotai/kimi-k2.5-0127"
api_type
"completions"
id
"gen-1770565877-YEl7SozqonTqaGI4rnTK"
upstream_id
"chatcmpl-6988b0f50362885b09107267"
total_cost
0.0162698
cache_discount
0.000034
upstream_inference_cost
0
provider_name
"Moonshot AI"
Evaluation details
Result
Evaluator
Details
Meta Data
6.0907%
Matches word count
n/a
neededClean
false
words
223
99.6814%
Dialogue to Total Word Ratio
Ratio: 92.38%, Deviation: 2.38%
neededClean
false
wordsTotal
223
wordsDialogue
206
52.8861%