NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-07-01KWZ5Y9DANBJH0X7V0GCDZ9MK
Run Details
Model:
Aion 3.0 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
21.8s
Cost:
$0.001539
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 200 word scene that has 90% 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
Okay, walk me through it again, Bill said, adjusting his ski mask. Were hitting the Johnson twins eighth birthday. Seventh, Molly corrected, studying a blueprint of a backyard. Birthday parties are a goldmine. Unsupervised presents, distracted parents, sugar-crash timing. Goldmine of Legos and My Little Ponies. Which we resell for actual gold. The targets the gift table. Its always by the grill, away from the bounce house. How do we get in? We dont look like seven-year-olds. We dont need to. Were the Wacky Wilsons Balloon Animal Extravaganza. I have the van, the uniform, and a forged permit. A balloon animal van? Bill asked. Those things are a liability. A poodle pops, the whole gig is blown. Which is why our distraction is better. While Im making a giraffe, you crawl under the tablecloth. Under a tablecloth? In a crowd of kids? Thats not a heist, thats a game of hide-and-seek Im going to lose. Fine. Youll be the magicians assistant. I saw a set online. You go into a box, I saw you in half, you sneak out the back panel. Saw me in half? Thats a two-hour recovery time. The party is ninety minutes. Exactly. Youre out of the box by minute fifteen, you have seventy-five minutes to empty the table. And the kid who is getting sawed in half? Fake blood and a tantrum. Parents will be busy. Its perfect. Bill sighed. I miss when we robbed banks. Banks have alarms. The biggest threat here is a sugar-fueled stampede at the mention of cake.
created_at
"2026-07-07T20:57:30.81Z"
7/7/2026, 8:57:30 PM
model
"aion-labs/aion-3.0-mini-20260707"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
673
moderation_latency
(null)
generation_time
21637
tokens_prompt
77
tokens_completion
1163
native_tokens_prompt
66
native_tokens_completion
1066
native_tokens_completion_images
(null)
native_tokens_reasoning
774
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
0.0015386
router
(null)
provider_responses
0
endpoint_id
"0ad7ab68-a351-4a96-b2ef-fa8fe13adae3"
id
"42c1eecf91664887a6e6e63bc1deec32"
is_byok
false
latency
638
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-1783457850-NLUFplBPyRdaw3pL2ikW"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783457850-pHOZc8hcirN629nWiUxG"
upstream_id
"42c1eecf91664887a6e6e63bc1deec32"
total_cost
0.0015386
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
257
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 90.00%
neededClean
false
wordsTotal
265
wordsDialogue
0
0.0000%