NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-27-01M5YEM3CQG9QY5N0GAQRHF8RT
Run Details
Model:
Kimi K3.1 Pro (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
5m 30s
Cost:
$0.100392
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 30% 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
From the road, number twelve looked less like a target than a cake that had achieved sentience. Balloons crowded the gate. A cardboard giraffe sagged beside the door, and from the garden came the delighted shriek of a bouncy castle accepting another victim. Molly crouched behind the hedge with a notebook. Bill crouched beside her, mostly because his borrowed clown trousers made standing inadvisable. “Remind me,” Bill said, “why we are robbing people whose main source of income is the tooth fairy?” Molly did not look up. “Because the blue bicycle is worth eight hundred pounds, and because you spent our last job’s proceeds on a jet ski.” “It was nearly a jet ski.” “It was a kayak with a horn.” A warm wind carried the smell of jelly and cut grass across the road. Somewhere beyond the hedge, an adult began blowing up balloons with the weary rhythm of a man reconsidering every decision since university. Bill’s red shoes had curly toes and enough space to accommodate a small family. Molly had chosen a black waitress uniform, reasoning that nobody ever questioned a woman carrying a tray, even when the tray contained rope. Molly flattened a drawing across her knee. It showed the house, the marquee, and several small figures fleeing what appeared to be a haunted teapot. She tapped the teapot. “The presents go into the marquee at two. At two oh five, the magician starts. At two ten, you set off the sprinkler.” “And the children?” Bill asked. “Run inside for cake. We collect the gifts, leave through the side gate, and meet you at the van.” Bill leaned closer. “Why does your drawing show me being chased by a swan?” “That is not part of the plan. That is a prediction.” Behind them, their getaway vehicle waited beneath a sycamore: a white van with HONEST TERRY’S BOUNCY CASTLES painted on the side. Honest Terry was neither honest nor present. He was at a wedding in Leeds, unaware that Bill had borrowed his van, his costume, and, through an administrative misunderstanding, his dignity. Molly checked her watch. Ninety seconds remained before the magician was due to begin, assuming he had survived the parking. Bill opened his mouth, possibly to object, but the front gate swung wide. A woman wearing a badge that said BIRTHDAY COMMANDER surveyed them over an armful of paper plates. “Are you the entertainers?” Molly closed the notebook. Her smile became bright, professional, and criminally expensive. “Of course,” she said. “He does balloons. I do miracles.” Bill looked at his trousers, then at the marquee, where a mountain of presents shimmered like a dragon’s hoard. “I want the kayak back,” he whispered. “First we steal the bicycle. Then you can buy a louder kayak, you ridiculous, ridiculous man.” Inside the garden, a trumpet kazoo sounded. Bill sighed, picked up the balloon pump, and followed her towards the gate with the grave expression of a man approaching glory, execution, and a committee of tiny critics.
created_at
"2026-10-27T10:31:16.134Z"
10/27/2026, 10:31:16 AM
model
"moonshotai/kimi-k3.1-pro-20261023"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2110
moderation_latency
(null)
generation_time
329772
tokens_prompt
75
tokens_completion
9848
native_tokens_prompt
146
native_tokens_completion
10010
native_tokens_completion_images
(null)
native_tokens_reasoning
9337
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
0.100392
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.22.1; linux; x64))"
http_referer
(null)
request_id
"req-1793097076-PvTfDWcSsiJnTn5Jozyw"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1793097076-ZYVEhxgOx40ilJIZ9BQH"
upstream_id
"chatcmpl-6ae07d74fa96422aa9027bd9"
provider_responses
0
endpoint_id
"a3fafaac-f097-4ef1-86b3-842854dad5c6"
id
"chatcmpl-6ae07d74fa96422aa9027bd9"
is_byok
false
latency
2110
model_permaslug
"moonshotai/kimi-k3.1-pro-20261023"
provider_name
"Moonshot AI"
status
200
total_cost
0.100392
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: 30.00%, Deviation: 0.00%
neededClean
false
wordsTotal
500
wordsDialogue
150
100.0000%