NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37PYQNXENVRPNDRVXMVRC16
Run Details
Model:
Aion 3.5 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
20.3s
Cost:
$0.004669
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
90.48%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
45.2419%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 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
Molly crouched behind a hedge shaped like a giraffe, binoculars pressed to her face, while Bill ate a sandwich beside her. "Bill, put down the sandwich. We're on a job." "I plan better when I eat. It's a known fact. Einstein invented relativity over a meatball sub." "That's not even remotely true." Molly lowered the binoculars and pointed across the park. "Okay, look. The party's at three. Bouncy castle, clown, cake table near the oak tree. The presents go on that folding table by the piñata." Bill chewed thoughtfully. "What kind of clown?" "What does that matter?" "Molly. Clowns are a variable. Is it a birthday clown or a corporate clown? A corporate clown has nothing to lose." "It's a seven-year-old's birthday party, Bill." "Even worse. Amateur hour. Amateur clowns are unpredictable." Molly snatched the sandwich out of his hands. "Focus. We go in as caterers. I've got the uniforms, the van, the whole thing. We load the presents into Tupperware containers labeled 'extra napkins' and wheel them out on a cart." Bill stared at her with genuine hurt. "You stole my sandwich." "You stole a carousel horse in 2019. We're even." "That horse had sentimental value." He sighed and pulled a folded napkin from his jacket, which he had apparently brought as a backup sandwich. "Fine. Caterers. But what about the kids? Kids notice things. Kids are like tiny, sticky detectives." "That's why we're bringing the big guns." Molly reached into her bag and pulled out a massive lollipop the size of a dinner plate. Bill's eyes went wide. "The Distraction Deluxe. Where did you get that?" "I know a guy. One kid sees this, they all swarm. We toss it into the bouncy castle, and we have exactly four minutes." "Four minutes to grab every present?" Bill shook his head. "The piñata's a problem. Kids mob the piñata candy. That's a choke point between us and the table." "Which is why you'll be on piñata duty. When it breaks, you help 'clean up' the candy, which clears a path for me." Bill put a hand over his heart. "You want me to elbow children out of the way?" "No, Bill, I want you to hand them candy like a hero while I work. You're the friendly caterer. I'm the invisible one." "You're never invisible. You're six feet tall and you walk like you're in a western." "That's called presence." "That's called a wanted poster." Molly checked her watch. "Two o'clock. We move in twenty minutes. Remember, no real names, no eye contact with the clown, and whatever happens, do not eat the cake." Bill froze mid-bite of his backup sandwich. "Why not? What's wrong with the cake?" "Because if you eat the cake, we're not thieves anymore, Bill. We're monsters." He nodded solemnly and tucked the sandwich away. "For the record, I'm only doing this because rent is due." "Tell it to the judge, partner. Now get in the van." The giraffe hedge watched them go, silent as ever, though anyone looking closely might have sworn it disapproved.
created_at
"2026-09-23T18:02:57.611Z"
9/23/2026, 6:02:57 PM
model
"aion-labs/aion-3.5-20260923"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1300
moderation_latency
(null)
generation_time
20258
tokens_prompt
75
tokens_completion
826
native_tokens_prompt
65
native_tokens_completion
770
native_tokens_completion_images
(null)
native_tokens_reasoning
71
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
0.00466875
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790186577-WmQehpFOYvnEgevhjd6Q"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790186577-sns88OeidqV0AZjHj8l0"
upstream_id
"7415c58a0e6446e8822820326e5b0df1"
provider_responses
0
endpoint_id
"09b1fc56-3888-42bd-b7a0-926851c7f9d6"
id
"7415c58a0e6446e8822820326e5b0df1"
is_byok
false
latency
1300
model_permaslug
"aion-labs/aion-3.5-20260923"
provider_name
"AionLabs"
status
200
total_cost
0.00466875
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
90.48%
Matches word count
n/a
neededClean
false
words
510
0.00%
Dialogue to Total Word Ratio
Ratio: 73.29%, Deviation: 23.29%
neededClean
false
wordsTotal
513
wordsDialogue
376
45.2419%