NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-27-01M5YEC3HR2PVB4K0A7EAB4DBG
Run Details
Model:
Kimi K3.1 Pro (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
2m 36s
Cost:
$0.053602
Provider:
Moonshot AI
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
69.96%
Dialogue to Total Word Ratio
(details)
84.6660%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 70% 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 spread the plan across the dashboard: a paper napkin, three jelly beans, and a crayon drawing of a bouncy castle. Outside, children shrieked beneath a banner reading HAPPY SIXTH BIRTHDAY, POPPY! Bill adjusted his top hat. “Which jelly bean am I?” “The green one.” “Why am I green?” “Because you felt sick after casing the party.” “I wasn’t sick. I was evaluating the cake.” “You evaluated four slices.” “Thoroughly. What’s the red jelly bean?” “The birthday girl.” “And the black one?” “The clown.” Bill stopped adjusting his hat. “There’s a clown?” “Ignore the clown.” “I can’t ignore a clown. That’s how clowns get you.” “Focus. At two fifteen, I enter as a balloon artist. You follow as a magician.” “Bill the Incomprehensible.” “Just Bill is incomprehensible enough. Can you do a magic trick?” “I can make money disappear.” “That’s called gambling.” “Not when I do it. When I do it, people applaud, then check their pockets.” “Fine. I’ll gather everyone near the bouncy castle with balloon animals.” “You can’t make balloon animals.” “I can make balloon snakes.” “That’s just a balloon.” “Not with my confidence.” “Then you create a diversion.” “I pull a rabbit from my hat.” “You don’t have a rabbit.” “I pull your hat from my hat.” “What’s under my hat?” “A smaller hat.” “Bill.” “It’s hats all the way down. They’ll be mesmerized.” “While everyone’s watching you, I’ll move the presents to the van.” “All of them?” “All of them.” “Even the big one shaped like a pony?” “Ponies aren’t rectangular.” “It might be an efficient pony.” “Use the pillowcases. And don’t take the cake.” “What if the cake is a present?” “The cake is never a present.” “It was present at breakfast.” “Bill.” “Sorry. Professional habit. What’s the signal if something goes wrong?” “I sneeze three times.” “You always sneeze three times.” “Then I’ll sneeze four.” “That’s not a signal. That’s an ambulance.” “Fine. I’ll shout, ‘What a lovely party!’” “That sounds like something I’d shout at a lovely party.” “It’s a children’s party. How lovely can it be?” A knock rattled Bill’s window. A woman in a paper crown stood outside, smiling with the exhausted menace of someone who had iced thirty cupcakes before dawn. Bill lowered the window. “Are you two the entertainers?” she asked. “No,” said Bill. “Yes,” said Molly. “We’re here to steal the—” “Show!” Molly said. “He’s here to steal the show. I’m here to supervise him, which is considerably harder.” The woman narrowed her eyes. Bill produced a balloon from his sleeve and handed it over. “A snake,” he said. “It’s a worm.” “A junior snake.” She led them toward the garden. Molly grabbed the napkin plan and hissed, “New plan. You do the diversion. I take the presents.” Bill tucked the black jelly bean into his pocket. “What about the clown?” “Still ignore him.” From the bouncy castle came a slow, honking laugh. Bill paled. “He’s in the castle.” “Then I’m going to need a bigger hat.” Molly decided not to ask why.
created_at
"2026-10-27T10:26:54.146Z"
10/27/2026, 10:26:54 AM
model
"moonshotai/kimi-k3.1-pro-20261023"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
5068
moderation_latency
(null)
generation_time
155898
tokens_prompt
75
tokens_completion
5411
native_tokens_prompt
146
native_tokens_completion
5331
native_tokens_completion_images
(null)
native_tokens_reasoning
4527
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
0.053602
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.22.1; linux; x64))"
http_referer
(null)
request_id
"req-1793096814-Wau24QLNZgfI66wgfZMe"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1793096814-ETcylNw2nDDfC55UzJK3"
upstream_id
"chatcmpl-6ae07c6e468768f625b88fb8"
provider_responses
0
endpoint_id
"a3fafaac-f097-4ef1-86b3-842854dad5c6"
id
"chatcmpl-6ae07c6e468768f625b88fb8"
is_byok
false
latency
5068
model_permaslug
"moonshotai/kimi-k3.1-pro-20261023"
provider_name
"Moonshot AI"
status
200
total_cost
0.053602
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
99.38%
Matches word count
n/a
neededClean
false
words
505
69.96%
Dialogue to Total Word Ratio
Ratio: 72.67%, Deviation: 2.67%
neededClean
false
wordsTotal
505
wordsDialogue
367
84.6660%