NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ00W3E8FDNXZZMYVPKQQQV2
Run Details
Model:
MoonshotAI: Kimi K2.6
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3m 23s
Cost:
$0.025322
Provider:
SiliconFlow
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
98.87%
Dialogue to Total Word Ratio
(details)
96.2603%
Overall
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
Molly adjusted her goggles. "You’re certain the target is unconscious by eight?" Bill nodded. "Positive. Little Timmy’s turning five. Cake at seven, sugar crash by seven-thirty, total parental blackout by eight. Easy pickings, Molly." "Security?" "One clown, unarmed, emotionally devastated by balloon animals and poor career choices." "Loot assessment?" "Stacked. Legos, a train set, three talking dinosaurs, and what the invite called a ‘surprise big gift.’" Molly’s eyes gleamed. "Entry point?" "Side yard is a no-go. Chihuahua minefield. We rappel from the oak tree, drop onto the present table, stuff the sacks, and exfil past the bouncy castle." "Why is there always a bouncy castle?" "Because joy is a structural weakness. Wear the purple wig. If caught, you’re Aunt Linda from Des Moines." "I hate Aunt Linda." "She brought tuna casserole and crippling debt. Now sync watches. The piñata detonates at twenty hundred hours." "That’s not a piñata, Bill. That’s a hornets’ nest." "Exactly. Nobody pursues a thief covered in hornets." Molly tightened her harness. "I want double hazard pay." "You get juice boxes and glory. Try not to cry when the clown sees you." "Last time was a medical allergy."
created_at
"2026-04-24T15:13:59.762Z"
4/24/2026, 3:13:59 PM
model
"moonshotai/kimi-k2.6-20260420"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
907
moderation_latency
(null)
generation_time
202584
tokens_prompt
77
tokens_completion
5998
native_tokens_prompt
69
native_tokens_completion
6314
native_tokens_completion_images
(null)
native_tokens_reasoning
6015
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"
usage
0.02532155
router
(null)
provider_responses
0
endpoint_id
"6ebc1d51-2760-4277-8c1e-c8ce9e01c18e"
id
"019dc00e0f9150c99fd3e2c01e215e8a"
is_byok
false
latency
892
model_permaslug
"moonshotai/kimi-k2.6-20260420"
provider_name
"SiliconFlow"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777043639-CZqEEC7MpWvJ1C4YFBe4"
session_id
(null)
api_type
"completions"
id
"gen-1777043639-wIUfeGGZttn5SCJK3A2e"
upstream_id
"019dc00e0f9150c99fd3e2c01e215e8a"
total_cost
0.02532155
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SiliconFlow"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
93.65%
Matches word count
n/a
neededClean
false
words
191
98.87%
Dialogue to Total Word Ratio
Ratio: 93.26%, Deviation: 3.26%
neededClean
false
wordsTotal
193
wordsDialogue
180
96.2603%