NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-07-01KWZ4883KH05VVC716MV0PRTP
Run Details
Model:
Aion 3.0 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
34.5s
Cost:
$0.001457
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0001%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 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
Bill scratched his neck. “That fence has a ‘World’s Best Grandma’ sticker on it. We can’t climb that. It’s sacred ground.” “It’s a sticker, Bill. Not a force field.” Molly adjusted her binoculars. “We slip in during the cake cutting, grab the loot and out the back fence.” “What if the rabbit sees us?” “Rabbits don’t talk, Bill. They nibble. We wear the clown costumes from the van. Blending in.” Bill chewed his lip. “My nose is too big for the red one. It’ll look suspicious. Like I’m a sad clown with a fake nose on a real nose.” “Just pull it over your actual nose. It’s called layering.” Molly checked her watch. “Game time. Remember: we’re after the LEGO sets. Not the glitter markers. We have standards.” “Fine. But if I get snot on a balloon animal, you’re explaining that to the therapist.” “The therapist we can’t afford because we keep striking out on jobs like this?” “We’re not a team of failure junkies, Molly. We’re artists.” “Artists who are about to steal a five-year-old’s birthday presents.” “She’ll learn,” said Bill, adjusting his oversized clown collar. “Disappointment builds character.” Molly stopped. “Her name’s Chloe. She’s turning six. And we’re stealing her new unicorn bedspread.” Bill’s painted smile faltered. “Is it at least a cool unicorn? Or one of those creepy realistic ones?” “It’s rainbow vomit and a golden horn.” “Alright. Let’s hit it.”
created_at
"2026-07-07T20:28:00.003Z"
7/7/2026, 8:28:00 PM
model
"aion-labs/aion-3.0-mini-20260707"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
573
moderation_latency
(null)
generation_time
34339
tokens_prompt
77
tokens_completion
1094
native_tokens_prompt
66
native_tokens_completion
1008
native_tokens_completion_images
(null)
native_tokens_reasoning
680
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
0.0014574
router
(null)
provider_responses
0
endpoint_id
"0ad7ab68-a351-4a96-b2ef-fa8fe13adae3"
id
"7c46cf8ff5af46c69fb7aeff5dc8095a"
is_byok
false
latency
573
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-1783456080-3wUVCILHqbEsFTT2jU7K"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783456080-CNNLj34jm0bpN5AthU44"
upstream_id
"7c46cf8ff5af46c69fb7aeff5dc8095a"
total_cost
0.0014574
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
234
0.00%
Dialogue to Total Word Ratio
Ratio: 87.71%, Deviation: 37.71%
neededClean
false
wordsTotal
236
wordsDialogue
207
0.0001%