NC Bench
Overview
About
Tests
Models
Model
MoonshotAI: Kimi K2.5
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2026-02-08-01KGZ04VTYQP4BW8W1ZHZV2FC4
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 absolutely positive the payout justifies this profound level of indignity?" Bill asked, tightening his shoelaces. "It’s a toddler birthday on the Upper East Side," Molly said, checking her watch. "The registry literally has a pony listed. An actual pony, Bill." "What about the civilian witnesses?" "Twenty children under four with attention spans of goldfish. We infiltrate as entertainment. You’re Bippo the Sad Clown, I’m Princess Sparklefists the Merciless." "I specifically told you last week that I don’t do balloon animals." "You’ll juggle. Terribly. While I stuff decorative sacks with unopened gaming consoles." "What’s the security situation?" "One half-blind grandpa and a deflating bounce house. The real danger is the mob mentality immediately post-cake cutting." "Primary escape route?" "Through the bouncy castle, over the vinyl fence, into the alley. I already cut the blower motor." "Contingency if we’re caught?" "Immediate hysterical tears. Blame childhood trauma. They’ll offer therapy vouchers, not handcuffs." "Why do I specifically have to wear the red nose?" "Because you’ve got the natural temperament for existential dread. The red really suits you." "I genuinely hate you with every fiber of my being right now." "Grab the gift sacks. The piñata drops in five minutes."
created_at
"2026-02-08T16:08:51.59877+00:00"
Sunday, February 8th, 2026 at 4:08:51 PM GMT+00:00
model
"moonshotai/kimi-k2.5-0127"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
793
moderation_latency
(null)
generation_time
58196
tokens_prompt
61
tokens_completion
2938
native_tokens_prompt
68
native_tokens_completion
2957
native_tokens_completion_images
(null)
native_tokens_reasoning
2793
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
0.0088778
router
(null)
provider_responses
0
id
"chatcmpl-6988b4d9af3a105cc7a16843"
status
200
is_byok
false
latency
793
endpoint_id
"49762299-66fd-4514-b0ee-c9e11e231e3b"
provider_name
"Moonshot AI"
model_permaslug
"moonshotai/kimi-k2.5-0127"
api_type
"completions"
id
"gen-1770566872-oudKCoKhHBSHtMN85fgd"
upstream_id
"chatcmpl-6988b4d9af3a105cc7a16843"
total_cost
0.0088778
cache_discount
0.000034
upstream_inference_cost
0
provider_name
"Moonshot AI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9990%
Matches word count
n/a
neededClean
false
words
199
94.0585%
Dialogue to Total Word Ratio
Ratio: 94.97%, Deviation: 4.97%
neededClean
false
wordsTotal
199
wordsDialogue
189
97.0288%