NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD5HR6EQ45HBF8H7H12JTE8
Run Details
Model:
MoonshotAI: Kimi K3 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 28s
Cost:
$0.045269
Provider:
Moonshot AI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
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 crouched behind the piƱata truck, binoculars fogging from birthday cake breath. Across the lawn, thirty presents glittered like loot in a dragon's daycare. Bill wore a clown nose over his ski mask and looked profoundly unemployable. "Plan is simple," Molly whispered. Bill nodded. "We bounce in, grab gifts, bounce out." "That's eleven words of plan and none of them good," she said, though technically it was eight. A balloon popped; both felons screamed into a handful of streamers. Molly mapped escape routes: past the magician, under the bouncy castle, through the emotional support pony. Bill suggested disguising himself as a large card. She suggested he aspire to furniture. Inside, children shrieked with joy, which complicated the moral atmosphere considerably. Still, rent was due, and the tiny wrapped boxes practically jingled. Molly checked her watch, adjusted her stolen party hat, and promised Bill that if anybody cried, they would leave one nice sock. Then the conga line turned toward the hedge. Somewhere a mother blew a kazoo like a battlefield trumpet, and every adult reached for coffee strong enough to file taxes beside the truly suspiciously damp gift table. Molly hated childhood nostalgia most during payroll. Crime smelled like frosting.
created_at
"2026-07-25T17:35:43.829Z"
7/25/2026, 5:35:43 PM
model
"moonshotai/kimi-k3-20260715"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2950
moderation_latency
(null)
generation_time
87389
tokens_prompt
75
tokens_completion
3098
native_tokens_prompt
147
native_tokens_completion
3015
native_tokens_completion_images
(null)
native_tokens_reasoning
2735
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
0.0452691
router
(null)
provider_responses
0
endpoint_id
"650c9b12-7b6d-444d-8d92-df8daef84d7a"
id
"chatcmpl-6a64f3f11d2ea393a90e4c2c"
is_byok
false
latency
2950
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-1785000943-hVp71YHTxGl5vGx1uMPF"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785000943-mavlZUVzSG1GYgnc94PY"
upstream_id
"chatcmpl-6a64f3f11d2ea393a90e4c2c"
total_cost
0.0452691
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
100.00%
Matches word count
n/a
neededClean
false
words
200
100.00%
Dialogue to Total Word Ratio
Ratio: 10.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
20
100.0000%