NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-07-01KWZ3WHQNMPYKE2YC3Q4N13AE
Run Details
Model:
Aion 3.0 Mini
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
35.2s
Cost:
$0.001644
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
46.8262%
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 squinted through the rain-streaked window of the rusted-out sedan. “Okay, run it by me again. From the top.” Bill shifted the binoculars. “It’s not complicated. We wait until ‘Magic Marvin’ starts his balloon-animal segment. That’s the high-traffic zone. Every single parent will be looking at the little brats getting giraffes.” “And the presents?” “Stacked on the picnic table by the bounce house. Unattended. It’s a thirty-second dash from the hedge line.” Molly scratched her chin, considering. “Thirty seconds is a long time, Billy boy. What if a kid needs a poo and the parent breaks formation to escort them to the port-a-potty?” “Then we abort,” Bill said flatly. “We don’t abort. We adapt. We have the cover.” “The clown suits.” Molly sighed. “I hate the clown suits.” “They are a brilliant piece of misdirection. No one notices the janitor. They notice the weird van. They notice the single guy with a camera. No one notices the two sad clowns smoking behind the maintenance shed.” “We don’t smoke.” “We will learn to smoke for the job. We look bored. We look local.” Molly turned from the window, her face pinched. “Bill. We are stealing presents from a birthday party. A kid named ‘Liam’ is turning six. There will be a cake with a fire truck on it.” “Don’t get soft on me.” “I’m not soft. I’m strategic. What if one of these gifts is a live pet? A hamster? Then we have to steal the hamster too. We don’t have a cage.” “We can get a cage.” “Where, Bill? Where are we going to get a cage at three in the afternoon? Is there a cage store on the way?” Bill lowered the binoculars. “You’re getting hung up on hypotheticals. The data says this is a gold mine. Look at the wrapping paper on that rectangular one. That’s a tablet. The big one with the lumpy bow? That’s a Lego set. We can flip those for six hundred bucks, easy.” Molly chewed her lip. “And the colt? The little pony they have tethered to the apple tree?” “We are not stealing the pony.” “Why not? It’s technically a present.” “Because you cannot fit a pony into a duffel bag! Use your head, Molly! Use the schematic I drew!” “Your schematic looks like a drunk bee made it.” “My schematic is a masterwork of spatial intelligence.” “It’s a napkin. With ketchup stains.” “The ketchup is a scale marker!” Bill snapped, throwing his hands up. He took a breath. “Look. The magician starts in eight minutes. We go in as Clover and Bubbles. We look pathetic. We steal the haul. We are in the wind before the first ‘braaap’ from the balloon giraffe. It’s a clean job.” Molly was quiet. She turned back to the window. The party was in full swing. A little girl was crying into her mother’s skirt, clutching a broken balloon. “Fine. No pony.” “Thank you.” “But I want the tiara. The little pink one with the fake gems.” “It’s probably plastic.” “I don’t care. It’s mine.”
created_at
"2026-07-07T20:21:36.647Z"
7/7/2026, 8:21:36 PM
model
"aion-labs/aion-3.0-mini-20260707"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
644
moderation_latency
(null)
generation_time
35067
tokens_prompt
77
tokens_completion
1285
native_tokens_prompt
66
native_tokens_completion
1141
native_tokens_completion_images
(null)
native_tokens_reasoning
457
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
0.0016436
router
(null)
provider_responses
0
endpoint_id
"0ad7ab68-a351-4a96-b2ef-fa8fe13adae3"
id
"765b23d198f74905b7eb189fcd952dd4"
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-1783455696-TPPrGWslL9ONDwWGyzLw"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783455696-lKCwcUThtRy78orWnyXR"
upstream_id
"765b23d198f74905b7eb189fcd952dd4"
total_cost
0.0016436
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
93.65%
Matches word count
n/a
neededClean
false
words
509
0.00%
Dialogue to Total Word Ratio
Ratio: 84.50%, Deviation: 14.50%
neededClean
false
wordsTotal
516
wordsDialogue
436
46.8262%