NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-24-01M39WRFERY199FCB5A19GQQ29
Run Details
Model:
Aion 3.5 Mini (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 15s
Cost:
$0.004851
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
98.46%
Dialogue to Total Word Ratio
(details)
99.2276%
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 spread the blueprint across the van's hood. "Okay, Billy-boy. The Henderson kid's turning seven. Saturday. Bouncy castle, pony rides, forty presents." Bill peered at the diagram. "A pony? We're stealing from a pony party?" "We're stealing from the presents table. The pony stays." "What's the security situation?" "One dad in a Hawaiian shirt. He's already drunk on Capri Suns." "Capri Suns don't—" "Don't question the intel, Bill." "Fine. What's the actual extraction plan?" "You wear the mascot costume." "Why do I always wear the mascot costume?" "Because you've got the shoulders of a cartoon raccoon." "That raccoon has a tail, Molly. I can't work a tail." "Clip it on, tuck it in, waddle to the present table, fill the sack, waddle out." "Kids will hug me, Molly." "Let them. It builds cover." "One of them bit me last time! Drew blood! At a communion!" "Then be faster this time." "What if the birthday boy opens everything before I get there?" "Then you grab the cake too. We sell slices by the pound." "This is why my therapist quit, you know." "Your therapist was stealing our cut." "She was seven, Molly." "Everyone's on the payroll, Bill. Now practice your waddle."
created_at
"2026-09-24T14:22:52.902Z"
9/24/2026, 2:22:52 PM
model
"aion-labs/aion-3.5-mini-20260923"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1395
moderation_latency
(null)
generation_time
74735
tokens_prompt
75
tokens_completion
3015
native_tokens_prompt
65
native_tokens_completion
3457
native_tokens_completion_images
(null)
native_tokens_reasoning
2701
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
0.0048515
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1790259772-8U5Gz91bGfsQOadUwmcW"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790259772-Gg7ADpwA39Ed7qmyAM9C"
upstream_id
"b6200f2178c14e2892fba42f2e8bfea2"
provider_responses
0
endpoint_id
"60ac3bdc-90ec-4769-9193-2c00b4d79562"
id
"b6200f2178c14e2892fba42f2e8bfea2"
is_byok
false
latency
1395
model_permaslug
"aion-labs/aion-3.5-mini-20260923"
provider_name
"AionLabs"
status
200
total_cost
0.0048515
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
100.00%
Matches word count
n/a
neededClean
false
words
200
98.46%
Dialogue to Total Word Ratio
Ratio: 93.53%, Deviation: 3.53%
neededClean
false
wordsTotal
201
wordsDialogue
188
99.2276%