NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37PE8KG0MSEZW66E4XBNT11
Run Details
Model:
Aion 3.5 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
15.5s
Cost:
$0.004363
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
99.95%
Dialogue to Total Word Ratio
(details)
96.8015%
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
Molly peered through the bushes at the backyard full of screaming children. "Okay, Bill, this is it. Operation Birthday Bonanza." "Molly, we're stealing presents from children." "Technically, we're repossessing them for the greater good." "Which is?" "My rent. Now put on your clown nose." "I'm not putting on the nose." "You put on the nose, Bill, or you blow the whole thing." "We're behind a hedge. Nobody can see us." "Put. On. The. Nose." "Fine. Fine. There. Happy?" "Thrilled. Now, we walk in, blend with the parents, and fill the pillowcase." "What pillowcase?" "The one you're supposed to be holding." "I thought you were bringing the pillowcase!" "Bill." "What was I supposed to do, steal one from the birthday boy's bed? He's right there, Molly. Sleeping. In a crown." "Then improvise. Use your pants." "My pants?" "Stuff the presents down your pants." "That's not a heist, that's a crime against tailoring." "Would you rather explain to a six-year-old why you're touching his presents?" "There's a piñata. Maybe I could hide the loot in the piñata." "That's not how piñatas work." "Everything's how piñatas work if you believe, Molly." "Grab the shiny one with the bow and run. I'll create a diversion." "What diversion?" She pushed him into the yard.
created_at
"2026-09-23T17:53:57.889Z"
9/23/2026, 5:53:57 PM
model
"aion-labs/aion-3.5-20260923"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
883
moderation_latency
(null)
generation_time
15374
tokens_prompt
75
tokens_completion
782
native_tokens_prompt
65
native_tokens_completion
719
native_tokens_completion_images
(null)
native_tokens_reasoning
445
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
0.00436275
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790186037-SctImdYhmYbsxCCFu3tr"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790186037-jclWJADfwtEcEvnXTxeu"
upstream_id
"c5e82d8a383b49fcb69a0429c88a5cef"
provider_responses
0
endpoint_id
"09b1fc56-3888-42bd-b7a0-926851c7f9d6"
id
"c5e82d8a383b49fcb69a0429c88a5cef"
is_byok
false
latency
883
model_permaslug
"aion-labs/aion-3.5-20260923"
provider_name
"AionLabs"
status
200
total_cost
0.00436275
cache_discount
0.00014625
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
93.65%
Matches word count
n/a
neededClean
false
words
209
99.95%
Dialogue to Total Word Ratio
Ratio: 91.47%, Deviation: 1.47%
neededClean
false
wordsTotal
211
wordsDialogue
193
96.8015%