NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-07-01KWZ4KPJV88273NJRQN418E2C
Run Details
Model:
Aion 3.0 Mini
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
21.0s
Cost:
$0.001068
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
0.01%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0049%
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 at the invitation, her nose wrinkling. “It says ‘Maggie’s Magical Seventh Birthday Spectacular.’ Bill, I’m not wearing a fairy costume.” “No, no, no. You’re thinking too literal.” Bill paced the stolen van, which smelled of old cheese and desperation. “We aren’t *attending* the party. We are the party’s logistical arm.” “We’re the what?” “The event staff. I’ve got a forged certificate from ‘Party Pizzazz.’ We’re the ‘Balloon and Bounce House Specialists.’ And you,” he said, pointing a greasy finger at her, “are the face of a corporate conglomerate that lost its soul.” “I don’t follow,” she said. “You’re not a fairy. You’re a manager. A clipboard. A tired smile. A soul-crushing uniform polo shirt.” Molly looked down at her black turtleneck. “I don’t own a polo shirt.” “We’ll get one. From a lost and found. It’s part of the character. You’re there to supervise the ‘fun.’ I’m there to fix the bounce house when it ‘breaks.’” “But the plan is to steal the presents,” Molly said slowly. “Not to inflate a sad piece of vinyl.” “That’s the beauty, Mol! We get the layout. We see where the ‘Thank You’ gift bags are stacked. We identify the weak-eyed parents. Then, while I am ‘troubleshooting’ the air pump by the dessert table, you have a ‘medical emergency.’ A small one. A fainting spell. You’re allergic to the glitter. You need to sit down in the quiet room.” “The quiet room doesn’t have presents.” “No! The quiet room is where the host, Brenda, keeps the *spare* presents. The ones for the kids who couldn’t come. I saw the spreadsheet on her Facebook. She’s a meticulous planner. It’s a flaw.” Molly chewed her lip. “And the loot itself? How do we get a hundred tiny craft kits and a dozen Barbie Dream Houses out without anyone noticing?” Bill grinned. He held up a roll of industrial-grade, clear plastic sheeting. “We don’t steal the gifts. We steal the *wrapping*. The contents are worthless. The real value is the three hundred dollars in custom-printed, holographic unicorn paper that Brenda spent six hours on. She posted a tutorial. We take the paper. The kids get a naked toy. The parents have a meltdown. We sell the paper on Etsy to sad, overworked parents for a premium.” Molly stared at him. “You planned a heist around the *wrapping paper*.” “It’s the biggest score of the season! It’s untraceable, high-margin, and psychologically damaging. Now, are you in or are you in?” “I need a clipboard,” she sighed. “And a thicker polo shirt. That glitter allergy might be real.” “That’s my girl. Now, we have three hours. Let’s go practice your disappointed-parent grimace. Remember, the eyes have to say ‘I care about your child’s safety,’ while the hands say ‘I am pocketing a roll of Elsa’s face.’”
created_at
"2026-07-07T20:34:15.279Z"
7/7/2026, 8:34:15 PM
model
"aion-labs/aion-3.0-mini-20260707"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
905
moderation_latency
(null)
generation_time
20837
tokens_prompt
77
tokens_completion
794
native_tokens_prompt
66
native_tokens_completion
730
native_tokens_completion_images
(null)
native_tokens_reasoning
10
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
0.0010682
router
(null)
provider_responses
0
endpoint_id
"0ad7ab68-a351-4a96-b2ef-fa8fe13adae3"
id
"186771d888434afeb8946cfe46ff5b83"
is_byok
false
latency
902
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-1783456455-YZ9lJQzxBlv7MLHtGHf9"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783456455-6hEXANC8LvtINtDr2s6B"
upstream_id
"186771d888434afeb8946cfe46ff5b83"
total_cost
0.0010682
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
0.01%
Matches word count
n/a
neededClean
false
words
469
0.00%
Dialogue to Total Word Ratio
Ratio: 86.74%, Deviation: 16.74%
neededClean
false
wordsTotal
475
wordsDialogue
412
0.0049%