NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-07-01KWZ5D1Q7D1WH2WHRVV2H9BN9
Run Details
Model:
Aion 3.0
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
14.2s
Cost:
$0.004623
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
90.48%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
45.2419%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 30% 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
"Let me get this straight," Bill whispered, peering through the binoculars at the house down the street. "We're going to rob a children's birthday party." Molly slapped the binoculars down, her eyes narrowed. "Keep your voice down. And yes, it's the perfect heist. Nobody suspects a thing at a kid's party. Everyone's distracted by cake and screaming and those little scream things." "Party poppers?" "Whatever. The point is, little Tyler's parents went all out this year. I'm talking electronics. I'm talking cash in the cards. I'm talking one of those ride-on cars that costs more than my actual car." "Which one? The red one or the blue one?" "Does it matter? Both are worth at least four hundred on Craigslist." Bill shifted on the bush they were hiding behind, wincing as a branch poked him in a sensitive area. "I don't know, Molly. Stealing from kids? That's got to be a new low, even for us." Molly turned to face him, her expression dead serious. "Bill, we are professionals. We don't discriminate based on age. If anything, we're teaching these kids a valuable life lesson about not trusting strangers and guarding their valuables." "Sure, that's one way to look at it." "Bill." "Right. Professionals. So what's the plan?" Molly pulled a crumpled napkin from her jacket pocket and unfolded it, revealing a crude map drawn in what looked like crayon. "We go in through the side gate. The bouncy castle is in the backyard, which means all the adults will be supervising the chaos out there. The presents are in the living room, piled next to the gift table. We grab, we bag, and we're out before anyone notices." "What if someone notices?" "Then you start crying and say you're looking for the bathroom. People get uncomfortable when a grown man cries, especially at a kid's party. They'll just point you somewhere and leave you alone." "That's actually brilliant." "I know. Now, here's the critical part." Molly tapped the napkin. "There's a clown." Bill's face went pale. "A clown?" "A clown." "What kind of clown? Like a happy clown or a creepy clown?" "Is there a difference?" Bill swallowed hard. "I can't do clowns, Molly. You know that. Ever since that incident at the circus when I was eight—" "Get over it. The clown is scheduled to do a balloon animal show from three to three-thirty. That's our window. While the kids are watching Mr. Twists-a-Lot make a giraffe out of latex, we hit the living room." "And if the clown sees us?" Molly paused, considering this. "Then we take him out too." Bill's eyes widened. "Take him out? You mean kill a clown? At a children's party?" "I meant tie him up, Bill. God. What kind of monster do you think I am?" She stuffed the napkin back into her pocket. "Now put on your disguise. You're Uncle Steve." "Who's Uncle Steve?" "Nobody knows. That's the beauty of it."
created_at
"2026-07-07T20:48:05.885Z"
7/7/2026, 8:48:05 PM
model
"aion-labs/aion-3.0-20260707"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
619
moderation_latency
(null)
generation_time
14046
tokens_prompt
77
tokens_completion
820
native_tokens_prompt
67
native_tokens_completion
737
native_tokens_completion_images
(null)
native_tokens_reasoning
67
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
0.004623
router
(null)
provider_responses
0
endpoint_id
"8c8f827d-2bef-468a-8f9e-8e27b470de5e"
id
"6ac7467340914b3ea6094a9070158e7b"
is_byok
false
latency
617
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-1783457285-ElQ1allZOr6hkSVULEdC"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783457285-KEYV3tj9LMutx3MGL7l5"
upstream_id
"6ac7467340914b3ea6094a9070158e7b"
total_cost
0.004623
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
90.48%
Matches word count
n/a
neededClean
false
words
490
0.00%
Dialogue to Total Word Ratio
Ratio: 80.57%, Deviation: 50.57%
neededClean
false
wordsTotal
494
wordsDialogue
398
45.2419%