NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD7PCG06TW8ZE7E6CHMBVNA
Run Details
Model:
MoonshotAI: Kimi K3 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
27.3s
Cost:
$0.011594
Provider:
Moonshot AI
Evaluation summary
Score
Evaluator
Details Link
75.16%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
87.5766%
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
The invitation had been stolen from a stroller, laminated by juice, and it promised a magician, a bouncy castle, and enough wrapped loot to retire badly. Molly flattened it on the laundromat table while Bill sorted socks with the intensity of a man defusing bombs. “We go in as clowns,” Molly whispered. Bill held up one sequined shoe the size of a canoe. “I’m not wearing the shoes.” “Fine. Guard the cake.” “Why does crime smell like frosting?” Outside, children shrieked like tiny sirens. The plan was elegant in the way falling downstairs is elegant: distract the parents with bubbles, bribe the magician with coupons, compliment the birthday dinosaur, then liberate every present before the piñata achieved consciousness. Molly packed a decoy gift containing three potatoes and a note. Bill practiced his innocent face, which made nearby pigeons file complaints. He insisted the piñata could see. Molly insisted socks were not evidence. Together they approached the fence, bowing to a balloon animal as if it were clergy. The castle exhaled. Somewhere a kazoo began the heist anthem. Bill stepped into a cupcake and pretended it was tactical.
created_at
"2026-07-25T18:13:12.84Z"
7/25/2026, 6:13:12 PM
model
"moonshotai/kimi-k3-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2277
moderation_latency
(null)
generation_time
26996
tokens_prompt
75
tokens_completion
836
native_tokens_prompt
147
native_tokens_completion
770
native_tokens_completion_images
(null)
native_tokens_reasoning
504
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
0.0115941
router
(null)
provider_responses
0
endpoint_id
"650c9b12-7b6d-444d-8d92-df8daef84d7a"
id
"chatcmpl-6a64fcba1d2ea393a90e530c"
is_byok
false
latency
2277
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-1785003192-LtlEKUnODXxhQLw8Xnbc"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785003192-86ZoZ1Ohwltm4BUfcyLT"
upstream_id
"chatcmpl-6a64fcba1d2ea393a90e530c"
total_cost
0.0115941
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
75.16%
Matches word count
n/a
neededClean
false
words
187
100.00%
Dialogue to Total Word Ratio
Ratio: 10.70%, Deviation: 0.70%
neededClean
false
wordsTotal
187
wordsDialogue
20
87.5766%