NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-07-01KWZ423RD7NAGGXDQ651WQ60A
Run Details
Model:
Aion 3.0
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2m 38s
Cost:
$0.058599
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
94.57%
Dialogue to Total Word Ratio
(details)
95.2807%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
"So let me get this straight," Bill said. "We're breaking into a child's birthday party?" "Six-year-old's party," Molly corrected. "Rich kid. Massive haul." "Six-year-olds don't have nice stuff." "Kid's dad runs some tech company. We're talking gaming consoles, tablets, drones. Two grand minimum." "And security?" "A clown and a bouncy castle." "The clown could be a problem." "Bill, the clown makes balloon animals." "What if he's a violent clown?" "Then we bribe him. Everyone has a price." Molly slid a photo across the table. "We go in as caterers. White shirts, black pants, aprons. I posed as a health inspector, menu's confirmed. Pizza, cake, juice boxes." "Juice boxes. Premium grade crime." "During musical chairs, we load the present table into the van." "Musical chairs lasts forty seconds." "Exactly. Forty seconds of distraction. You grab, I cover." "What about the kids?" "What about them?" "Can they identify us?" "Bill, it's a room full of six-year-olds. We'll be 'the pizza people.' They won't remember past naptime." "What if one starts crying?" "Crying isn't a security system. Move fast." "This feels wrong." "This feels profitable. Different thing. Practice your pizza face." "My pizza face?" "Friendly. Invisible. Trustworthy." "I'm a thief, Molly." "Tonight, you're a thief who delivers pizza. There's a difference."
created_at
"2026-07-07T20:24:38.943Z"
7/7/2026, 8:24:38 PM
model
"aion-labs/aion-3.0-20260707"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
718
moderation_latency
(null)
generation_time
157908
tokens_prompt
77
tokens_completion
8987
native_tokens_prompt
67
native_tokens_completion
9733
native_tokens_completion_images
(null)
native_tokens_reasoning
8608
native_tokens_cached
0
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
0.058599
router
(null)
provider_responses
0
endpoint_id
"8c8f827d-2bef-468a-8f9e-8e27b470de5e"
id
"05b0b2476a164925bb6e0c211ab92d32"
is_byok
false
latency
718
model_permaslug
"aion-labs/aion-3.0-20260707"
provider_name
"AionLabs"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1783455878-LbhV5TTGf8j7mFyQeYhd"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783455878-pWTzcXepGdDWyt2MdKUH"
upstream_id
"05b0b2476a164925bb6e0c211ab92d32"
total_cost
0.058599
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AionLabs"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
95.99%
Matches word count
n/a
neededClean
false
words
208
94.57%
Dialogue to Total Word Ratio
Ratio: 94.86%, Deviation: 4.86%
neededClean
false
wordsTotal
214
wordsDialogue
203
95.2807%