NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-07-01KWZ432TA1JCW1BKF74B576P0
Run Details
Model:
Aion 3.0
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
16.1s
Cost:
$0.005517
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 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 black ski mask in the rearview mirror. "I still think we should have gone with the cat burglar look. Black turtlenecks are classic." "Classic, sure, but not practical for a party full of sticky-fingered six-year-olds," Bill said from the passenger seat. He consulted a crudely drawn map on his knee. "You want to blend in, you wear what they wear." "Which is what, exactly? Spider-Man costumes? Princess dresses?" "We're going as clowns, Molly. We've been over this." "I look ridiculous in face paint." "You look ridiculous now. Face paint can only help." Bill paused. "Besides, clowns can carry enormous bags. Nobody questions a clown with a bag." "That's because clowns are terrifying." Molly turned off the ignition. "And what if the kids get suspicious? What if one of them asks us to make a balloon animal?" "You make a balloon animal. How hard can it be?" "Last time you tried to inflate a balloon, you passed out for forty-five seconds." "It was humid. The air was dense." Molly rolled her eyes and pulled on her oversized polka-dot shoes. "Fine. But I'm not making balloon animals. If they ask, I'll say I'm a specialized clown. A minimalist clown." "There's no such thing as a minimalist clown." "Now there is. What's the entry plan?" "Front door." Bill pulled out a crumpled invitation. "Kid named Toby. His mom is apparently one of those parents who invites the whole class so nobody feels left out." "So nobody feels left out of having their presents stolen by two middle-aged people in face paint." "We're not middle-aged. We're experienced." "Experienced what? Failures?" Bill sighed. "I have a clean record." "You have a clean record because you've never successfully committed a crime." "The law doesn't specify success. Absence of conviction is absence of conviction." Bill put on his rainbow wig, which tilted to one side. "How do I look?" "Like a mentally unstable candy cane. What's the exit strategy if things go sideways?" "Out the back through the bounce house." "The bounce house? Bill, there will be children in the bounce house." "Then we bounce with the children." "That's insane." "That's adaptability." Bill opened the car door and adjusted his enormous red nose. "Listen, the presents are in the back room. We go in, we fill the bag, we tell everyone we're entertainment for the party, we collect our things, we leave. Thirty minutes tops." "Have you ever successfully stolen anything?" "Once, a pen from a bank." "That's not theft, Bill. That's office supplies." "The teller looked upset." "Because you were wearing a fake mustache for no reason!" Bill slammed the door. "I was conducting reconnaissance. And the mustache stayed on for the full twenty minutes, which is more than I can say for the wig at last week's practice run." Molly grabbed her oversized bag and sighed. "If we get caught, I'm telling them you kidnapped me." "With what? A balloon sword?" "Don't tempt me. Let's go steal Christmas from a child." "It's a birthday party, Molly." "It's all the same to me." They waddled toward the house, oversized shoes slapping against the pavement, rainbow wigs bouncing in the afternoon light. Somewhere inside, a child laughed. Somewhere outside, two clowns prepared to commit their first felony.
created_at
"2026-07-07T20:25:10.744Z"
7/7/2026, 8:25:10 PM
model
"aion-labs/aion-3.0-20260707"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
522
moderation_latency
(null)
generation_time
16010
tokens_prompt
77
tokens_completion
1066
native_tokens_prompt
67
native_tokens_completion
886
native_tokens_completion_images
(null)
native_tokens_reasoning
187
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
0.005517
router
(null)
provider_responses
0
endpoint_id
"8c8f827d-2bef-468a-8f9e-8e27b470de5e"
id
"f5bac5281c304514a6370283e9a26a32"
is_byok
false
latency
522
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-1783455910-Havned9uopueMydxh4G3"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783455910-e0NZVlQ6hCcQQwLGlJwt"
upstream_id
"f5bac5281c304514a6370283e9a26a32"
total_cost
0.005517
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
0.00%
Matches word count
n/a
neededClean
false
words
543
0.00%
Dialogue to Total Word Ratio
Ratio: 78.58%, Deviation: 28.58%
neededClean
false
wordsTotal
551
wordsDialogue
433
0.0000%