NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ02PXVB96HM3X43BHQTY17Q
Run Details
Model:
MoonshotAI: Kimi K2.6
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
2m 4s
Cost:
$0.045391
Provider:
Cloudflare
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9985%
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, which were covered in glitter from a previous heist. "You sure this is the right house, Bill? The invite said pony rides and a bouncy castle." Bill checked his clipboard, frowning at the crayon drawing taped to the front. "Positive. Target is six, allergic to gluten, and owns a PS5." He tugged at his stolen clown nose and straightened his wig. "Why are we dressed like this again?" "Because children's parties have better security than banks," Molly hissed, pointing at a seven-year-old doorman with a juice box and suspicious glare. "We blend in or we get made." "We look like serial killers." "We look like entertainment." She shoved a garbage bag into his trembling hands. "Now remember: grab presents, avoid the piñata—it's a distraction—and if anyone asks, you're Professor Wigglesworth." Bill sighed, adjusting his suspenders and checking his escape route. "I did time for bank fraud, Molly. Actual bank fraud." "And tonight," she beamed, clipping a balloon to his ear and checking her watch, "you're stealing fourteen copies of 'Frozen' and a science kit. Move out." They belly-crawled across the lawn, directly into the path of a screaming sprinkler and certain humiliation.
created_at
"2026-04-24T15:46:07.351Z"
4/24/2026, 3:46:07 PM
model
"moonshotai/kimi-k2.6-20260420"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
381
moderation_latency
(null)
generation_time
123716
tokens_prompt
77
tokens_completion
9991
native_tokens_prompt
69
native_tokens_completion
11332
native_tokens_completion_images
(null)
native_tokens_reasoning
9670
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
0.04539118
router
(null)
provider_responses
0
endpoint_id
"85e7870f-601c-4891-98ab-f7ac2ed4d718"
id
"id-1777045567737"
is_byok
false
latency
381
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-1777045567-mlyfyD95NqurnCTRITXZ"
session_id
(null)
api_type
"completions"
id
"gen-1777045567-EpuPQ8WnEWNhMe09t6j9"
upstream_id
"id-1777045567737"
total_cost
0.04539118
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
100.00%
Dialogue to Total Word Ratio
Ratio: 49.26%, Deviation: 0.74%
neededClean
false
wordsTotal
203
wordsDialogue
100
99.9985%