NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-07-01KWZ338DS2QREF9SV403KEKF8
Run Details
Model:
Aion 3.0
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
38.5s
Cost:
$0.010923
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9595%
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 old takeout and regret. Molly unrolled the blueprint across the dashboard, weighted down one corner with a half-eaten burrito, and the other with Bill's elbow. "Operation Happy Birthday commences at exactly 14:00 hours," Molly announced. Bill scratched his stubble. "That's two in the afternoon. You know I can't tell military time." "That's why I said both, Bill. Now, the target is seven-year-old Tyler Williams, and the haul should be approximately twenty-three presents." "Twenty-three? How do we know it's exactly twenty-three?" "His mother posted the guest list on Facebook, Bill. Each guest brings one present. Plus, the parents. Plus grandma, who's bringing something big. The woman loves a sale at Toys 'R' Us." "Toys 'R' Us went bankrupt, Mol." "My point is, the grandma overcompensates. Now, we go in through the backyard, where the bouncy castle is set up. You'll need the pink wig." "I'm not wearing the wig again. The kids tried to braid it last time." Bill shifted in his seat. The truth was, he wasn't great with kids, and he was even worse with bouncy castles. "Bill, the wig is essential. You're 'Aunt Tracy' today." "Since when do I look like a Tracy?" "Since we needed a character with zero backstory who can blend into the background while I cut through the gift table with surgical precision." Bill shifted uncomfortably. "The parents will notice." "They won't. At the height of the party, the parents are exhausted. The key distraction is the cake. When they bring out the ice cream cake—and I've confirmed it's ice cream cake, not regular cake—everyone looks toward the birthday boy. We have a forty-second window." "Forty seconds to grab twenty-three presents?" "We're taking the whole table. I've got the dolly in the back." Bill's eyes went wide. "You're going to wheel out a whole table of presents in front of everyone?" "Not in front of everyone. Through the side gate. The same way the caterer came in." "There's a caterer?" "It's a nice party, Bill. There's a caterer, a face painter, and a woman dressed as Elsa from Frozen who looks like she's been crying. This is a professional operation, which means we need to act professional." "I don't know, Molly. It feels wrong stealing from kids." "Kids don't buy their own presents, Bill. They don't appreciate them. Half those toys end up unopened in a closet by next Tuesday. We're rescuing them. We're giving them a purpose." "By fencing them on eBay?" "By giving them a second life with buyers who'll truly value them. And if we get twenty-three gifts at an average resale value of thirty dollars each, that's almost seven hundred dollars." "Six hundred ninety," Bill corrected. "Math wasn't supposed to be your thing." Molly checked her watch. "The party starts in forty-five minutes. Put on the wig." Bill groaned but reached for the pink curls on the dashboard. "This is the last time." "That's what you said at the Bar Mitzvah."
created_at
"2026-07-07T20:07:47.911Z"
7/7/2026, 8:07:47 PM
model
"aion-labs/aion-3.0-20260707"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
562
moderation_latency
(null)
generation_time
38228
tokens_prompt
77
tokens_completion
2106
native_tokens_prompt
67
native_tokens_completion
1787
native_tokens_completion_images
(null)
native_tokens_reasoning
1320
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
0.010923
router
(null)
provider_responses
0
endpoint_id
"8c8f827d-2bef-468a-8f9e-8e27b470de5e"
id
"7ed1a535143641bf9a1dab8cf2049242"
is_byok
false
latency
562
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-1783454867-vWWKxIIvOBLsOY1RS5B0"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783454867-VXHxrw2ZvdZW1wH6jgi2"
upstream_id
"7ed1a535143641bf9a1dab8cf2049242"
total_cost
0.010923
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
99.92%
Matches word count
n/a
neededClean
false
words
497
0.00%
Dialogue to Total Word Ratio
Ratio: 84.02%, Deviation: 34.02%
neededClean
false
wordsTotal
507
wordsDialogue
426
49.9595%