NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-24-01M39WNYY8N6GX1BWM85164Z19
Run Details
Model:
Aion 3.5 Mini (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 1s
Cost:
$0.004602
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.57%
Dialogue to Total Word Ratio
(details)
99.7843%
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 spread the blueprints across the diner table, pinning corners with coffee mugs. The target: the Hendersons' annual birthday bash for their twins. Bounce house, pony rides, and a gazebo sagging under forty pounds of wrapped presents. Security was one teenage cousin in a llama costume and a grandmother with a walker who guarded the gift table like a dragon on a hoard. Bill considered her the wildcard. "The piñata is our window," Molly said. During the piñata, every child, parent, and pony would be staring at that donkey like it owed them money. Bill would cut the garden lights, Molly would sweep presents into laundry bags, and they'd vanish before the llama finished crying—apparently the costume made him emotional. "Llamas don't cry," Bill said. "It's a costume." Molly reviewed the escape route: over the neighbor's unsupervised trampoline, into the waiting hatchback. Their gear included two duffel bags, one crowbar, and a box of Get Well Soon cards for alibis, because nothing disarmed suspicion like apparent condolences. Bill tapped the map. "If the grandma fights?" "God help us," Molly said. It wasn't their classiest job. But rent was due, and the twins had terrible taste in toys anyway.
created_at
"2026-09-24T14:21:30.451Z"
9/24/2026, 2:21:30 PM
model
"aion-labs/aion-3.5-mini-20260923"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1473
moderation_latency
(null)
generation_time
61152
tokens_prompt
75
tokens_completion
2950
native_tokens_prompt
65
native_tokens_completion
3279
native_tokens_completion_images
(null)
native_tokens_reasoning
2639
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
0.0046023
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1790259690-iJAHLaLpyWr2QwKX0Zke"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790259690-kilq51yXa4TOMgjx44te"
upstream_id
"c83565c74bfe4fa6a1590bff3112df57"
provider_responses
0
endpoint_id
"60ac3bdc-90ec-4769-9193-2c00b4d79562"
id
"c83565c74bfe4fa6a1590bff3112df57"
is_byok
false
latency
1473
model_permaslug
"aion-labs/aion-3.5-mini-20260923"
provider_name
"AionLabs"
status
200
total_cost
0.0046023
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
99.57%
Dialogue to Total Word Ratio
Ratio: 12.56%, Deviation: 2.56%
neededClean
false
wordsTotal
199
wordsDialogue
25
99.7843%