NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-07-01KWZ4Q6YD85WNCBHPZW9T44BE
Run Details
Model:
Aion 3.0 Mini
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
4m 16s
Cost:
$0.015393
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 70% 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 lowered the binoculars and whistled low. “You see that? It’s a fortress, Bill. Bouncy castle, clown, a piñata shaped like a unicorn. They have security moms.” Bill rubbed his temples. “We’re stealing presents from a six-year-old’s birthday party.” “Presents are presents. These are premium. The invite said ‘Amazon wish list.’ We’re looking at a haul of at least seven hundred dollars.” “Seven hundred dollars for a pile of Frozen merch and plastic dinosaurs.” “Exactly. Easy money. Look, the plan is simple. You go in as the balloon animal guy.” Bill stared at her. “I don’t know how to make balloon animals.” “You make a sword. Kids love swords. That’s ninety percent of balloon animals. The other ten percent is dogs, and dogs are just sadder swords. You hand the birthday boy the sword. He swings it. It pops. He cries. Chaos ensues while I slip in through the side door with the empty gift sacks and collect the merchandise.” “Chaos,” Bill repeated. “At a child’s party. For a unicorn piñata.” “It’s a strategic distraction. Don’t overthink the target. A dollar is a dollar, whether it’s from a bank vault or an Elsa doll’s dress pocket.” “And if the sword doesn’t pop?” “Then you make a balloon giraffe, step on it, and make a pained grunting sound. It’s organic, Bill. Improv.” Bill pointed toward the backyard. “What about the clown?” “What about him?” “He’s a professional. He’ll spot a bad balloon animal across a snack table. He’s got a spray bottle and a rubber chicken. He’ll know.” “That’s where the knockout drug in the cotton candy machine comes in. A little snack for the clown before the party. He gets sleepy, goes for a lie-down in the backseat of his Miss Piggy-mobile, and you’re the sole entertainer. Star of the show.” Bill’s jaw went slack. “You have knockout drugs. For a children’s clown. You bought roofies for Miss Piggy.” “It’s a veterinary sedative. Very small dose. He’ll just get drowsy. Miss Piggy will be fine. Focus on the present pickup window. It’s after cake, before the candle blow-out. I’ll be two minutes, tops.” “And if a kid sees you stuffing Barbies into a sack?” “You’re wearing the gorilla costume I brought. After the crying starts from the popped balloon, you burst out of the side room wearing the gorilla suit, bang your chest, and start a loud, aggressive banana dance. Everyone looks at you. I leave out the back door with the loot. We meet at the van.” Bill closed his eyes. “So the entire plan hinges on me performing a banana dance in a gorilla suit while you rob a child.” “It hinges on you selling the dance, Bill. If you sell it, we win. If you just stand there like a pervert in a zoo costume, we lose. Are you an artist, or are you a pervert?” “I’m an accomplice to drugging a clown for a three-dollar unicorn piñata.” “That’s the spirit. Now get in character. We go in five.” Bill picked up the gorilla suit. It smelled like nachos. “I hate this job.” “No,” Molly said, adjusting her own plain-clothes disguise. “You hate honest paychecks. Now suit up. Elsa isn’t going to fund herself.”
created_at
"2026-07-07T20:36:10.341Z"
7/7/2026, 8:36:10 PM
model
"aion-labs/aion-3.0-mini-20260707"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
661
moderation_latency
(null)
generation_time
256216
tokens_prompt
77
tokens_completion
10470
native_tokens_prompt
66
native_tokens_completion
10962
native_tokens_completion_images
(null)
native_tokens_reasoning
9598
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
0.015393
router
(null)
provider_responses
0
endpoint_id
"0ad7ab68-a351-4a96-b2ef-fa8fe13adae3"
id
"bb3ae6e0e54742aaa41e47e2660507d3"
is_byok
false
latency
644
model_permaslug
"aion-labs/aion-3.0-mini-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-1783456570-XfNvYEZ4AHsGtsRSU0Fe"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783456570-qAxcsJEyzRTfgaBpCF22"
upstream_id
"bb3ae6e0e54742aaa41e47e2660507d3"
total_cost
0.015393
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
537
0.00%
Dialogue to Total Word Ratio
Ratio: 91.18%, Deviation: 21.18%
neededClean
false
wordsTotal
544
wordsDialogue
496
0.0000%