NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD7PEEVMNDP7TRRSJKFNFWZ
Run Details
Model:
MoonshotAI: Kimi K3 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
43.4s
Cost:
$0.022304
Provider:
Moonshot AI
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
99.80%
Dialogue to Total Word Ratio
(details)
99.8909%
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 spread the blueprint across Bill’s kitchen table, weighing it down with a rubber chicken and three unpaid parking tickets. The target was number six Gumdrop Lane, where a birthday party would be guarded by a magician, a bouncy castle, and a grandmother with suspiciously sharp elbows. Bill wore a trench coat over a dinosaur onesie because he believed layers created mystery. Molly had drawn the escape route in crayon, partly for camouflage and partly because pens felt too confident. Molly whispered, “We go in as clowns, grab gifts, leave before cake.” Bill nodded solemnly, then raised one finger. “My clown shoes squeak Morse code. Also, I’m allergic to balloon animals.” Molly stared at the map, at the tiny piñata she had labeled “loot cloud,” and at Bill’s brave, doomed face. Outside, an ice cream truck played a tune like a warning from the judiciary. A neighbor’s corgi watched through the blinds with the disappointed professionalism of a detective who had already solved the case and filed it under idiots. She folded the blueprint into a paper hat, set it on Bill’s head, and decided crime, like childcare, was mostly timing, snacks, and denying everything to a clown.
created_at
"2026-07-25T18:13:14.85Z"
7/25/2026, 6:13:14 PM
model
"moonshotai/kimi-k3-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2279
moderation_latency
(null)
generation_time
43311
tokens_prompt
75
tokens_completion
1542
native_tokens_prompt
147
native_tokens_completion
1484
native_tokens_completion_images
(null)
native_tokens_reasoning
1210
native_tokens_cached
147
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
0.0223041
router
(null)
provider_responses
0
endpoint_id
"650c9b12-7b6d-444d-8d92-df8daef84d7a"
id
"chatcmpl-6a64fcbc51c976030dd023f8"
is_byok
false
latency
2279
model_permaslug
"moonshotai/kimi-k3-20260715"
provider_name
"Moonshot AI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1785003194-GC3eKDXGlCfAkdTZWugD"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785003194-dAa1m6uSyFBgvuk0sjJ8"
upstream_id
"chatcmpl-6a64fcbc51c976030dd023f8"
total_cost
0.0223041
cache_discount
0.0003969
upstream_inference_cost
0
provider_name
"Moonshot AI"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
198
99.80%
Dialogue to Total Word Ratio
Ratio: 12.12%, Deviation: 2.12%
neededClean
false
wordsTotal
198
wordsDialogue
24
99.8909%