NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ02HCKNMWYZT07BCCVY0ZYD
Run Details
Model:
MoonshotAI: Kimi K2.6
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
2m 7s
Cost:
$0.042955
Provider:
Cloudflare
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
98.15%
Dialogue to Total Word Ratio
(details)
99.0770%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 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 adjusted her night vision goggles and frowned at the pastel fortress before them. Streamers hung like prison bars across the suburban lawn. "You said this was a bank, Bill." "It is a bank," Bill whispered, tightening his grip on a sack. "A bank of joy. Those presents are unregistered assets." "There's a bouncy castle." "Distraction infrastructure." A clown emerged from the garage juggling chickens. Molly ducked behind bushes, yanking Bill down with her. "We have codes for a reason. 'The eagle has landed' means go-time. 'The cupcake has sprinkles' means abort because it's a five-year-old's birthday party." Bill checked his clipboard. "I thought 'cupcake' meant the guard was eating dessert." "That's 'muffin,' you walnut." Molly sighed, watching a piƱata sway gently. "Fine. What's the exit strategy?" "Same as always. We go in as plumbers, claim there's a leak, and stuff the goodie bags." "We're dressed as ninjas." Bill looked down at his black tactical gear, then at the superhero theme. A toddler in a cape stared at them from the curb, clutching a juice box. "We'll say we're... dark Avengers?" Molly stood, brushing grass off her knees. "Give me the sack. If anyone asks, you're my emotional support burglar."
created_at
"2026-04-24T15:43:05.854Z"
4/24/2026, 3:43:05 PM
model
"moonshotai/kimi-k2.6-20260420"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
676
moderation_latency
(null)
generation_time
126822
tokens_prompt
77
tokens_completion
10465
native_tokens_prompt
69
native_tokens_completion
10723
native_tokens_completion_images
(null)
native_tokens_reasoning
10139
native_tokens_cached
3
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
0.04295518
router
(null)
provider_responses
0
endpoint_id
"85e7870f-601c-4891-98ab-f7ac2ed4d718"
id
"id-1777045386539"
is_byok
false
latency
675
model_permaslug
"moonshotai/kimi-k2.6-20260420"
provider_name
"Cloudflare"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777045385-MGRymiT0o3s9cMnxaEzK"
session_id
(null)
api_type
"completions"
id
"gen-1777045385-jkyNEsqqmxV4oS0nTvMU"
upstream_id
"id-1777045386539"
total_cost
0.04295518
cache_discount
0.00000237
upstream_inference_cost
0
provider_name
"Cloudflare"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
98.15%
Dialogue to Total Word Ratio
Ratio: 53.69%, Deviation: 3.69%
neededClean
false
wordsTotal
203
wordsDialogue
109
99.0770%