NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-27-01M5YH4XKK50YRG8JJTGFJAPSQ
Run Details
Model:
Kimi K3.1 Pro (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
5m 31s
Cost:
$0.119052
Provider:
Moonshot AI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
63.76%
Dialogue to Total Word Ratio
(details)
81.8814%
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 steering wheel. It was drawn on a paper plate. Bill peered through his clown wig. "Why am I a sausage?" "That's the van." "Why does the van have legs?" "That's you." "Oh." He scratched his painted nose. "I look surprised." "You are surprised. I discussed this twice." "I was checking the cake for listening devices." "You ate the cake." "Exactly. Nothing ever gets past me." Molly tapped the plate. "The party starts at two. We go in as magicians, keep everyone entertained, and leave with the presents." "All the presents?" "All the presents." "Even the big one with the bow?" "Especially the big one with the bow." "It looks heavy." "That's why I brought you." "I thought you brought me because I own a wig." "You found that wig in a skip." "A very good skip." Bill studied the plan again. "What's this bit labelled 'certain death'?" "The bouncy castle." "And this bit labelled 'worse than death'?" "Grandma." "Is she dangerous?" "She makes small talk." Bill shuddered. "Perhaps we could just tunnel in." "No tunnelling." "Disguise myself as a present?" "No." "A large present?" "Bill." "A modest present with realistic breathing holes?" Molly folded the plate in half. "We walk through the front door. You smile. I do tricks. You don't eat anything. Then we take the presents to the van." "That's your whole brilliant plan?" "Yes." "It lacks elegance." "You have a plastic flower that squirts water into your own ear." "It lacks elegance on my part, too, but I expected more from you." "What's my first trick?" "Making yourself scarce." "And my second?" "Making the presents scarce." "What about the children?" "Leave them where they are." "That hardly seems like a trick." "It's my specialty." "Can I saw the cake in half?" "No." "Can I eat the evidence?" "Only if it stops you talking." A fist knocked on the window. Outside stood a girl in a pirate hat. "Are you the magicians?" she asked. "Yes," said Molly. "No," said Bill. The girl narrowed her eyes. "Why is he dressed as a clown?" "He's my assistant," Molly said. "Why is he holding a sack?" "For assisting," said Bill. "What's in the sack?" "Other sacks." The girl considered this. "Toby's got handcuffs." Bill lowered his voice. "Toy ones?" The girl leaned closer. "He's six. Where would he get real ones?" Bill nodded wisely. "A toy shop." Behind her, someone released a dozen balloons. The bouncy castle shuddered as though waking up. Molly opened her door. "Remember: smile, magic, presents, van." "And if Grandma talks to me?" "Abandon the mission." "What about the presents?" "Abandon me." Bill climbed out, tripped over his oversized shoes, and bowed to the pirate girl. She pointed at his wig. "That looks like a dead ferret." Bill straightened. "Good. Then nobody will suspect it's alive." Molly closed her eyes. "Two minutes," she muttered. "We haven't even started, and I need a new plan." "Make it a bigger plate," Bill called.
created_at
"2026-10-27T11:15:24.412Z"
10/27/2026, 11:15:24 AM
model
"moonshotai/kimi-k3.1-pro-20261023"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1502
moderation_latency
(null)
generation_time
330766
tokens_prompt
75
tokens_completion
10767
native_tokens_prompt
146
native_tokens_completion
11876
native_tokens_completion_images
(null)
native_tokens_reasoning
11123
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
0.119052
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.22.1; linux; x64))"
http_referer
(null)
request_id
"req-1793099724-bgYOkzRRgAHV0IxnJZ0y"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1793099724-7XMNkh9HhxL3WfSv2y3W"
upstream_id
"chatcmpl-6ae087cdb7033f358251ccc9"
provider_responses
0
endpoint_id
"a3fafaac-f097-4ef1-86b3-842854dad5c6"
id
"chatcmpl-6ae087cdb7033f358251ccc9"
is_byok
false
latency
1502
model_permaslug
"moonshotai/kimi-k3.1-pro-20261023"
provider_name
"Moonshot AI"
status
200
total_cost
0.119052
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
63.76%
Dialogue to Total Word Ratio
Ratio: 73.00%, Deviation: 3.00%
neededClean
false
wordsTotal
500
wordsDialogue
365
81.8814%