NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37NT065A77RE3B4633CH3J8
Run Details
Model:
Aion 3.5 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
14.6s
Cost:
$0.004695
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
1.04%
Matches word count
(details)
0.07%
Dialogue to Total Word Ratio
(details)
0.5530%
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
The van smelled like cold pizza and bad decisions. Molly peered through binoculars at the backyard across the street, where a bouncy castle sagged in the wind like a defeated jellyfish. "Okay," she said, lowering the binoculars. "Twelve kids, one clown, and a piñata shaped like a dinosaur. This is going to be a cakewalk." Bill shifted in his seat, the tulle of his princess costume rustling against the seatbelt. "I still don't understand why I'm the one dressed as Elsa's grandmother." "Because I'm the distraction, and you're the grab man. We've been over this forty times." "You're the distraction? Molly, your plan is to walk through the gate and yell 'free ice cream.' That's not a distraction, that's a riot." Molly checked her reflection in the rearview mirror and adjusted her fake mustache. "Exactly. A riot is distracting." Bill rubbed his temples, dislodging a plastic tiara. "The presents are stacked under the gift table by the fence. I get in, I fill the sack, I get out. Ten minutes, tops. And Molly? No ice cream announcements. There is no ice cream. You're just going to make them cry." "Crying is also distracting." "Crying children attract mothers. Mothers attract cell phones. Cell phones attract the police. It's the circle of life, and I refuse to be eaten by it." Molly considered this, chewing on the end of her mustache. "Fine. New plan. I'll pose as the entertainment inspector. Nobody questions a woman with a clipboard and a mustache." "Everyone questions a woman with a mustache." "That's why they won't suspect the clipboard." She tapped her temple. "Layered deception, Billy." Bill stared at her for a long moment, then sighed the sigh of a man who had once robbed a bank wearing a hot dog costume and still considered it the highlight of his career. "You know what the worst part is? The worst part isn't the clown. The worst part is that we're stealing from children. Actual children. On little Tyler's birthday." "Tyler has forty-seven presents, Bill. I counted. Nobody needs forty-seven presents. His parents bought him a pony. A pony, Bill. We're basically Robin Hood." "Robin Hood gave to the poor." "We are the poor!" Bill opened his mouth, closed it, and adjusted his tiara with grim resignation. "Fine. But if that clown makes a balloon animal at me, I'm out. I have standards." "You once hid in a dumpster for six hours." "Standards," Bill repeated, "that are flexible." Molly popped the van door open and squared her shoulders. "Sync watches. Ten minutes, then meet back here. And Bill? You look beautiful." "Don't talk to me during a job," Bill muttered, stepping out onto the sidewalk, a six-foot princess with a burlap sack and a dream. Behind them, the dinosaur piñata swayed gently in the breeze, blissfully unaware of the chaos to come.
created_at
"2026-09-23T17:42:53.911Z"
9/23/2026, 5:42:53 PM
model
"aion-labs/aion-3.5-20260923"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
628
moderation_latency
(null)
generation_time
14592
tokens_prompt
75
tokens_completion
828
native_tokens_prompt
65
native_tokens_completion
750
native_tokens_completion_images
(null)
native_tokens_reasoning
115
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
0.004695
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790185373-Q4KYrOlZok8JvcHWCy14"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790185373-HYnmGncjRB14kiUoqllC"
upstream_id
"f2799bf7ba0a419a94b842204e7af3d9"
provider_responses
0
endpoint_id
"09b1fc56-3888-42bd-b7a0-926851c7f9d6"
id
"f2799bf7ba0a419a94b842204e7af3d9"
is_byok
false
latency
628
model_permaslug
"aion-labs/aion-3.5-20260923"
provider_name
"AionLabs"
status
200
total_cost
0.004695
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AionLabs"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
1.04%
Matches word count
n/a
neededClean
false
words
474
0.07%
Dialogue to Total Word Ratio
Ratio: 62.05%, Deviation: 12.05%
neededClean
false
wordsTotal
477
wordsDialogue
296
0.5530%