NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-07-01KWZ4X4EPW4N9Y9278EVSSTVS
Run Details
Model:
Aion 3.0
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
20.0s
Cost:
$0.005493
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 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 folded the map on the table, tapping her pen against the edge until Bill finally looked up from his crossword puzzle. "What?" Bill said. "What do you mean, what? We've got a job tomorrow, and you're doing a crossword puzzle." "I'm on break." "You've been on break for two hours. Now are you going to help me plan this or not?" Bill set down his pen with a sigh. "Fine. What's the job?" "Children's party. Wealthy neighborhood. All the presents are going to be in the back room." "Wait, we're robbing a children's party?" "Did I stutter?" "Molly, that's low. Even for us." "Oh, don't get moral on me now. You didn't have a problem with the retirement home last month." "That was different. Old people have insurance. These are kids." "These are rich kids. They'll get more presents next week. Probably have more than they know what to do with already." Bill scratched his chin. "What's the haul looking like?" "According to my research, the birthday boy's getting a PlayStation 5, a mountain bike, and enough Lego to build a replica of the Vatican." "Lego goes for good money secondhand." "See? Now you're thinking. So what's the plan?" "Same as always? You go in as the entertainment, I sneak through the back." "That's the problem. They've already hired a clown." "You could fight the clown." "I'm not fighting a clown, Bill. I have standards." "Since when?" "Since the incident at the fair. Anyway, we need a new angle. What if we go in as parents?" "Of what kid? We don't have a kid." "We could borrow one." "We are not borrowing a child for a heist. That's where I draw the line." "Fine. What about catering? I could pose as a server, slip something in the punch—" "We're not drugging children, Molly." "Sleepytime tea. Totally natural. Just enough to make them drowsy." "You're unhinged." "Then you come up with something better." Bill leaned back in his chair. "What time does the party start?" "Two o'clock. Goes until five." "OK, so here's the plan. I'll go in through the back fence while you keep watch from the car. The parents will be distracted with cake and games. I grab the goods, we're out before the ice cream melts." "That's a terrible plan. What if someone sees you?" "That's what the ski mask is for." "In August?" "It's a light ski mask." Bill picked up his crossword puzzle again. "That's good enough. Write it up." Molly shook her head. "This is why we're not married anymore."
created_at
"2026-07-07T20:39:24.393Z"
7/7/2026, 8:39:24 PM
model
"aion-labs/aion-3.0-20260707"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
455
moderation_latency
(null)
generation_time
19822
tokens_prompt
77
tokens_completion
1025
native_tokens_prompt
67
native_tokens_completion
882
native_tokens_completion_images
(null)
native_tokens_reasoning
354
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
0.005493
router
(null)
provider_responses
0
endpoint_id
"8c8f827d-2bef-468a-8f9e-8e27b470de5e"
id
"6bea9f898c6c449d90a71874da000270"
is_byok
false
latency
455
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-1783456764-3HAD3JHXlN62HwBYshaR"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783456764-UzgtAwuJ1jkIGbVb9Kcb"
upstream_id
"6bea9f898c6c449d90a71874da000270"
total_cost
0.005493
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
426
0.00%
Dialogue to Total Word Ratio
Ratio: 87.56%, Deviation: 17.56%
neededClean
false
wordsTotal
426
wordsDialogue
373
0.0000%