NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-27-01M5YEW5E0HW4XPV00WDWTGRNX
Run Details
Model:
Kimi K3.1 Pro (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
3m 37s
Cost:
$0.069472
Provider:
Moonshot AI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 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 unrolled the plan across the café table, pinning one corner beneath Bill’s tea and the other beneath a plate of offended toast. “That,” said Bill, “is a giraffe.” “It’s the community centre.” “It has hooves.” “Those are the emergency exits.” Bill leaned closer. The giraffe wore a party hat and had BOUNCY CASTLE written across its stomach in Molly’s meticulous handwriting. Around them, Saturday morning clattered pleasantly: cups, cutlery, and a waitress pretending not to listen. “Right,” Molly said. “Party starts at two. We arrive at one fifty as entertainers.” “We?” “You’re Marvellous Bill. I’m your assistant, Glitter.” “Why can’t I be Glitter?” “Because you cried when I put sequins on your balaclava.” Bill stirred his tea with the injured air of a man whose criminal genius had been repeatedly misunderstood. Molly tapped the giraffe’s left ear. “Presents go in the village hall here. At two twenty, during musical statues, you wheel in my magic cabinet. We load the gifts, cover them with a false bottom, and leave through the kitchen.” “And the children?” “Will be watching me saw you in half.” “No.” “It’s a metaphorical saw.” “It wasn’t metaphorical last time.” “You still have both eyebrows.” “Different eyebrows.” The waitress set down their bill and retreated at speed. Molly continued. “At two thirty, the clown arrives.” Bill frowned. “You’re the clown.” “I’m Glitter. The real clown is called Bongo. You’ll distract him.” “How?” “Tell him there’s a better party next door. Higher fee, fewer children, excellent parking.” “That sounds plausible.” “It’s my house.” Bill opened his mouth, then closed it. On the plan, Molly had drawn a small arrow from the kitchen to the getaway van. Beside it, in red ink, she had written: MIND THE PRIEST. “Why is there a priest?” “Christening party afterwards.” “And why is the van a helicopter?” “It isn’t. That’s Darren.” From the next table, an elderly woman moved her handbag closer. Bill sighed and folded his arms. “Fine. What’s my trick while you’re loading?” “Rabbit from a hat.” “We don’t have a rabbit.” “You have a hat.” “It’s a crash helmet.” “Then improvise.” Bill studied the guest list, turning it sideways as though the names might confess. His finger stopped beside one final, particularly ominous note. “One guest is bringing a present that ticks. Is that a problem?” “Only if it’s a bomb. If it’s a clock, we’re stealing it. If it’s a crocodile, you’re carrying it.” “Why am I always on livestock duty again?” At two o’clock, Marvellous Bill stood before thirty children in a sequinned waistcoat, holding a crash helmet and wishing he had become an accountant. Glitter gave him a dazzling smile from beside a cabinet suspiciously large enough to contain a bicycle, three games consoles, and the entire British rail network. “For my first miracle,” Bill announced, “I will produce a rabbit.” Nothing happened. A small girl raised her hand. “That’s a badger.” Bill looked down. The badger looked up. Behind him, Molly quietly revised the getaway time.
created_at
"2026-10-27T10:35:40.362Z"
10/27/2026, 10:35:40 AM
model
"moonshotai/kimi-k3.1-pro-20261023"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2229
moderation_latency
(null)
generation_time
216523
tokens_prompt
75
tokens_completion
6802
native_tokens_prompt
146
native_tokens_completion
6918
native_tokens_completion_images
(null)
native_tokens_reasoning
6159
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
service_tier
(null)
usage
0.069472
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.22.1; linux; x64))"
http_referer
(null)
request_id
"req-1793097340-hD0JB4rAqrjw8btaNtzb"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1793097340-2si7ej1ORMPLti8RgMGo"
upstream_id
"chatcmpl-6ae07e7d40fbf038f82b7c9d"
provider_responses
0
endpoint_id
"a3fafaac-f097-4ef1-86b3-842854dad5c6"
id
"chatcmpl-6ae07e7d40fbf038f82b7c9d"
is_byok
false
latency
2229
model_permaslug
"moonshotai/kimi-k3.1-pro-20261023"
provider_name
"Moonshot AI"
status
200
total_cost
0.069472
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Moonshot AI"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
500
100.00%
Dialogue to Total Word Ratio
Ratio: 50.00%, Deviation: 0.00%
neededClean
false
wordsTotal
500
wordsDialogue
250
100.0000%