NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-24-01M39WTXEHXYW774XGTW8KJ5H9
Run Details
Model:
Aion 3.5 Mini (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
1m 12s
Cost:
$0.004569
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.8722%
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
Molly spread the blueprints across the rickety card table in the back of their van, her finger tracing a path through what looked like a crayon drawing of a castle. "Okay, Bill, here's the layout. Bouncy castle in the back, snack table by the hedge, and the present pile is right there, next to the clown." Bill peered at the paper, squinting. "That's not a blueprint, that's a napkin. And that's not a clown, that's a stain from your coffee." "It's a very dangerous stain. Look at it. It has eyes." Bill leaned closer. The stain did, in fact, have eyes. "Fair point. How do we get in?" "That's the beautiful part." Molly pulled out a bright pink wig and a sparkly tutu from a duffel bag. "We're going as parents." Bill stared at her, then at the tutu. "I'm not wearing that." "You're wearing the tutu." "Why am I wearing the tutu?" "Because you lost the coin toss, and because you have the legs for it. I've seen you in shorts, Bill. You could be a professional." "I have chicken legs. You said so yourself. Last Tuesday." "Last Tuesday I was being sarcastic. This Tuesday I'm being strategic. Put on the tutu." Bill sighed and began pulling the tutu over his cargo pants. "And you? What's your disguise?" Molly held up a t-shirt with a cartoon dinosaur on it and a lanyard. "I'm a birthday party entertainer. 'Dazzling Dana, the Balloon Animal Lady.'" "You can't make balloon animals." "I watched a forty-minute tutorial. I can make a snake." "A snake isn't an animal, it's a worm with ambitions." "It's a balloon snake, Bill, and children love it. Now, the plan. I entertain the kids, you grab the presents, we meet at the van in eight minutes." "Eight minutes? What if the kids want more balloons?" "Then you make snakes. You watched the tutorial too." "I watched forty minutes of it. The other twenty minutes I was eating a sandwich." "The sandwich is not an excuse. The plan is simple. In, distract, grab, out. What could go wrong?" Bill paused, one leg still trapped in the tutu. "The clown." "The clown is a coffee stain." "The clown is real. I saw the flyer. 'Captain Giggle's Magic Show.' There's a real clown, Molly." Molly went pale. "A real clown." "A real clown." "We agreed. No jobs with real clowns. That's rule seven." "Rule seven, yes. But the payout is forty presents, Molly. Forty. Do you know what a gaming console goes for these days?" Molly stared at the napkin. The coffee stain clown seemed to stare back. "Fine. But if Captain Giggle makes a balloon animal better than my snake, we're leaving." "Deal," said Bill, adjusting the tutu. "Now, do I have glitter on my face? I feel like I have glitter on my face." "You have glitter everywhere. You have glitter in places glitter shouldn't be." "That's the spirit of the tutu, Molly. It demands sacrifice."
created_at
"2026-09-24T14:24:12.765Z"
9/24/2026, 2:24:12 PM
model
"aion-labs/aion-3.5-mini-20260923"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1486
moderation_latency
(null)
generation_time
72240
tokens_prompt
75
tokens_completion
3330
native_tokens_prompt
65
native_tokens_completion
3255
native_tokens_completion_images
(null)
native_tokens_reasoning
2612
native_tokens_cached
65
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
0.0045687
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1790259852-H2ESpSRwsHu4Cs472OCn"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790259852-JDE5pCdWfL9Q1jjUKHfR"
upstream_id
"cb317cfa1ba342e69c10ee0b06a48654"
provider_responses
0
endpoint_id
"60ac3bdc-90ec-4769-9193-2c00b4d79562"
id
"cb317cfa1ba342e69c10ee0b06a48654"
is_byok
false
latency
1486
model_permaslug
"aion-labs/aion-3.5-mini-20260923"
provider_name
"AionLabs"
status
200
total_cost
0.0045687
cache_discount
0.0000338
upstream_inference_cost
0
provider_name
"AionLabs"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
496
0.00%
Dialogue to Total Word Ratio
Ratio: 75.05%, Deviation: 25.05%
neededClean
false
wordsTotal
497
wordsDialogue
373
49.8722%