NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37PEJDT18D762SJMN8TR3VH
Run Details
Model:
Aion 3.5 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
18.4s
Cost:
$0.005047
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
6.09%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
3.0476%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 30% 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 adjusted her binoculars from behind the wheel of a van that absolutely did not say "Flowers by Irene" on the side, because she had thought of that problem in advance. Bill, in the passenger seat, was applying his third layer of white face paint. "Stop that," she said. "You look like a mime who lost a bet." "I'm a party clown. It's genius. Nobody questions a clown." "Everybody questions a clown. Clowns are the most questioned people on earth." Bill held up a rubber chicken and squeaked it at her, which Molly felt proved her point. Through the window of number fourteen Maple Crescent, they could see the full scale of the operation: a bounce house, a petting zoo, a table bearing a cake shaped like a fire truck, and approximately forty presents stacked in a pyramid that suggested the birthday child's parents had never once said no to anything. "Okay," Molly said, unrolling a hand-drawn map on the dashboard. "The presents are in the living room. The piƱata is the distraction. When they bring it out, every adult in that house will herd the children into the backyard like it's a fire drill. That's our window. Ninety seconds, in and out, through the side door." "What's the rubber chicken for?" "The chicken is not part of the plan, Bill." "The chicken could be part of the plan." "The chicken has never once been part of the plan in eleven years." Bill set the chicken down with visible hurt, then peered at the map. "What about the goat?" Molly paused. "What goat?" "There's a goat in the petting zoo. I did reconnaissance earlier. That goat is a criminal mastermind, Molly. I watched it eat a folding chair. It has no fear." "We are not recruiting a goat." "I'm just saying, a goat causes chaos. Chaos is our friend." "Chaos is your friend. Chaos is my coworker who shows up uninvited and ruins my spreadsheets." Outside, a scream erupted from the backyard, followed by the unmistakable clatter of a folding chair being destroyed. Molly and Bill both turned. The goat had escaped. Children were scattering like bowling pins, a man in a "World's Best Dad" apron was sprinting across the lawn with the desperate speed of a man who knew exactly what the goat was capable of, and in the confusion, nobody was watching the side door. Molly stared. Bill slowly picked up the rubber chicken and held it out to her like a peace offering. "Fine," she sighed, grabbing her duffel bag. "The chicken can come. But if it squeaks during the job, it's staying behind." "That's fair," said Bill. "That's all I've ever asked." They slipped out of the van and crept toward the house, two professionals, one rubber chicken, and behind them, the distant screams of a father losing a war he never chose.
created_at
"2026-09-23T17:54:07.947Z"
9/23/2026, 5:54:07 PM
model
"aion-labs/aion-3.5-20260923"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
486
moderation_latency
(null)
generation_time
18354
tokens_prompt
75
tokens_completion
927
native_tokens_prompt
65
native_tokens_completion
833
native_tokens_completion_images
(null)
native_tokens_reasoning
236
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
0.00504675
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790186047-iZ9VCLZpUPCfacynRuOB"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790186047-jQVcwpU9pncbS3WPhjGI"
upstream_id
"14ab774c109d41b49af30040f1e841fd"
provider_responses
0
endpoint_id
"09b1fc56-3888-42bd-b7a0-926851c7f9d6"
id
"14ab774c109d41b49af30040f1e841fd"
is_byok
false
latency
486
model_permaslug
"aion-labs/aion-3.5-20260923"
provider_name
"AionLabs"
status
200
total_cost
0.00504675
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
6.09%
Matches word count
n/a
neededClean
false
words
477
0.00%
Dialogue to Total Word Ratio
Ratio: 44.14%, Deviation: 14.14%
neededClean
false
wordsTotal
478
wordsDialogue
211
3.0476%