NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ07EPJVRXGB6D7E3HQW7VNN
Run Details
Model:
MoonshotAI: Kimi K2.6
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
2m 36s
Cost:
$0.054967
Provider:
Cloudflare
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
96.85%
Dialogue to Total Word Ratio
(details)
98.4234%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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, which were caked with glitter from the craft store reconnaissance. Bill sat beside her in the van, studying a crayon-drawn map of the suburban backyard. The target was a five-year-old named Tyler, whose parents had rented a bounce house and purchased every toy in a three-county radius. The loot would include remote-control cars, a train set, and something called a slime laboratory that Molly suspected was worth millions on the black market. "Remember, absolutely no witnesses at all," Molly said to Bill. She checked her watch and sighed nervously. Bill nodded, smearing camo paint on his nose. He had loaded the duffel bags with wrapping paper to muffle clinking sounds. The birthday cake was scheduled for three o'clock, which gave them a seventeen-minute window while everyone sang off-key and watched the candles die. Molly had disabled the sprinklers. Bill had bribed the clown with a rubber chicken full of cash. Everything was proceeding according to plan, except for the slight problem that neither of them had ever been invited to a party without a parole officer present. They fist-bumped. The slide whistle blew loudly. "Let's steal some LEGOs very quickly," Bill said to her.
created_at
"2026-04-24T17:09:00.648Z"
4/24/2026, 5:09:00 PM
model
"moonshotai/kimi-k2.6-20260420"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
423
moderation_latency
(null)
generation_time
155812
tokens_prompt
77
tokens_completion
12060
native_tokens_prompt
69
native_tokens_completion
13726
native_tokens_completion_images
(null)
native_tokens_reasoning
11752
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
0.05496718
router
(null)
provider_responses
0
endpoint_id
"85e7870f-601c-4891-98ab-f7ac2ed4d718"
id
"id-1777050541018"
is_byok
false
latency
423
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-1777050540-DmlvjhPzNBzZPfo6Fv8k"
session_id
(null)
api_type
"completions"
id
"gen-1777050540-ettixatVRtaAaeyJUdVn"
upstream_id
"id-1777050541018"
total_cost
0.05496718
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
96.85%
Dialogue to Total Word Ratio
Ratio: 5.77%, Deviation: 4.23%
neededClean
false
wordsTotal
208
wordsDialogue
12
98.4234%