NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-24-01M39X2TF9NBYQ74Z39N0W58D7
Run Details
Model:
Aion 3.5 Mini (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
4m 38s
Cost:
$0.020782
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
42.54%
Dialogue to Total Word Ratio
(details)
71.2278%
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
The van sat parked across from the Hendersons' cul-de-sac, its side panel reading "Balloon Buddies — Fully Insured!" Molly adjusted her clown nose and raised the binoculars. Across the street, a bouncy castle wobbled in the breeze like a smug inflatable fortress. "Security's tighter than I expected," Bill said. "It's a seven-year-old's birthday, Bill." "The pony is clearly a patrol unit." "Buttercup weighs less than the cake," Molly said. "Every fortress has a weakness." Bill unrolled his blueprint across the dashboard. "Yours is the pinata." Molly lowered the binoculars slowly. "You want to beat a pinata in front of thirty kids." "In disguise." "We're dressed as clowns, Bill." Bill looked wounded. "I distract the parents with balloon animals. You grab presents during the singing." He tapped the blueprint. "Happy Birthday takes forty seconds." "Then sing faster." Molly stared at him. "What about the cake table?" Bill went pale. "I forgot the cake table." "Amateur," Molly muttered, pulling on her rainbow wig. "Fine. I'll take the cake table. And Bill?" "If that pony so much as twitches, the job's off." Somewhere across the street, Buttercup whinnied. Both of them froze. Bill nodded solemnly and checked his water-squirting flower. "For the loot," he whispered. Molly groaned.
created_at
"2026-09-24T14:28:31.865Z"
9/24/2026, 2:28:31 PM
model
"aion-labs/aion-3.5-mini-20260923"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1665
moderation_latency
(null)
generation_time
277612
tokens_prompt
75
tokens_completion
12226
native_tokens_prompt
65
native_tokens_completion
14836
native_tokens_completion_images
(null)
native_tokens_reasoning
11888
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
0.0207821
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1790260111-4CnkVJCps7pKYzec8Y2b"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790260111-VmfbwKWk27UHEmQoqD5p"
upstream_id
"fddde2ac10414744bdc6fdf96eb77021"
provider_responses
0
endpoint_id
"60ac3bdc-90ec-4769-9193-2c00b4d79562"
id
"fddde2ac10414744bdc6fdf96eb77021"
is_byok
false
latency
1663
model_permaslug
"aion-labs/aion-3.5-mini-20260923"
provider_name
"AionLabs"
status
200
total_cost
0.0207821
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
99.92%
Matches word count
n/a
neededClean
false
words
203
42.54%
Dialogue to Total Word Ratio
Ratio: 59.62%, Deviation: 9.62%
neededClean
false
wordsTotal
208
wordsDialogue
124
71.2278%