NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-24-01M39W840J9BAPR3TFYFK66JVB
Run Details
Model:
Aion 3.5 Mini (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
55.0s
Cost:
$0.003590
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
94.92%
Dialogue to Total Word Ratio
(details)
97.4597%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 pressed binoculars to her face and studied the backyard through a gap in the hedge. Balloons bobbed. A pony wearing a party hat stamped ominously near the fence. Their disguises hung in the van behind them—one ladybug costume, one dinosaur costume, both sized generously. "Twenty presents, minimum." Bill crouched beside her, chewing a granola bar he'd lifted from a gas station that afternoon. Practice, he called it. "The pony's a problem." "The pony," Molly said, "is a morale issue. I'm worried about the clown." Bill's jaw stopped mid-chew. He'd had an incident with a clown in Reno. Neither of them discussed Reno anymore. They agreed, silently and forever, to route around clowns. A seven-year-old staggered past carrying a box bigger than himself toward a table already sagging under wrapping paper. Somewhere a child screamed with joy. Somewhere a mother yelled about cake. "We go at cake time. Chaos peak." Bill nodded and wrote PLAN on his wrist in Sharpie. He'd lost three heists to inadequate note-taking. Molly checked her watch as the birthday boy unwrapped a shiny new bike and the crowd oohed on cue. She felt nothing. Absolutely nothing. Professional nothing. "Bill, are you crying?" "No."
created_at
"2026-09-24T14:13:56.891Z"
9/24/2026, 2:13:56 PM
model
"aion-labs/aion-3.5-mini-20260923"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2009
moderation_latency
(null)
generation_time
54986
tokens_prompt
75
tokens_completion
2525
native_tokens_prompt
65
native_tokens_completion
2556
native_tokens_completion_images
(null)
native_tokens_reasoning
2212
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
0.0035901
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1790259236-afXfAFGaosHt2jQnkJi8"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790259236-zOsjrEMzAigmM0dWPRdg"
upstream_id
"7c34e5d6f3ef47959f60a8c961218c74"
provider_responses
0
endpoint_id
"60ac3bdc-90ec-4769-9193-2c00b4d79562"
id
"7c34e5d6f3ef47959f60a8c961218c74"
is_byok
false
latency
2009
model_permaslug
"aion-labs/aion-3.5-mini-20260923"
provider_name
"AionLabs"
status
200
total_cost
0.0035901
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
199
94.92%
Dialogue to Total Word Ratio
Ratio: 14.78%, Deviation: 4.78%
neededClean
false
wordsTotal
203
wordsDialogue
30
97.4597%