NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-24-01M39VVE3FH4SYFFZ356JVGN2Q
Run Details
Model:
Aion 3.5 Mini (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
47.1s
Cost:
$0.002031
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9595%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 70% 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
"Alright, Bill," Molly said, spreading the blueprints across the card table. "The target is Timmy Henderson's seventh birthday party." Bill frowned at the map. "A birthday party? We've hit casinos. Banks. A museum. Now we're stealing from a seven-year-old?" "We're not stealing from a seven-year-old. We're liberating presents from an over-attended social event." "There's a bouncy castle, Mol. How do you plan a perimeter breach on a bouncy castle?" "That's the decoy. Kids go in, they bounce, they exhaust themselves. Meanwhile, the presents pile up unattended on the gift table like a little fortress of shame." "A fortress guarded by whom, exactly? Mrs. Henderson?" "Mrs. Henderson is our problem. She's got eyes like a hawk and a laminated sign-in sheet." Bill rubbed his temples. "You want me to out-stealth a suburban mom with a clipboard." "I want you to out-stealth a suburban mom with a clipboard, yes. You'll wear the costume." Bill went pale. "The costume." "The costume." "I'm not wearing the dinosaur suit again, Molly. Last time I wore the dinosaur suit, I got tackled by a guy named Gary." "That was a mascot gig at a car dealership. This is art. You'll be the party clown." "Clowns give me hives." "Then the hives will be part of your character. You juggle, you distract, I bag the presents and exit through the moonbounce's blind spot." "And if a kid grabs my leg? Kids love clowns. Kids grab legs." "Then you do what clowns do. You honk the horn and keep moving." Bill stared out the window for a long moment. "What's the take, even? What are we getting? Legos? A Fisher-Price drone?" "Per my intel, one of the presents is a Nintendo Switch. Another is a dirt bike. A dirt bike, Bill. For a seven-year-old who can't reach the pedals." "We're stealing a dirt bike from a child." "We're stealing a dirt bike from a family that clearly has more money than sense. That dirt bike will feed us for a month." "It'll feed your fence for a month. I get a cut of a Nintendo Switch and trauma." "You'll get sixty percent because you're wearing the clown suit." Bill sighed, the deep sigh of a man who had already lost. "What's my clown name?" "Bobo." "Bobo. Of course it's Bobo." He pulled the clown nose out of the duffel bag and turned it over in his hands. "If I get arrested at a child's birthday party, I want you to know I'll name you in the deposition." "If you get arrested, I'll be long gone with the dirt bike." "That's very inspiring, Mol. Really. Team spirit." "Meet me Saturday at ten. Face paint on. Balloon animals ready." "Can I at least pick my own balloons?" "No. Balloons are tactical. You'll make dogs. Everyone trusts a dog balloon." Bill pocketed the nose and stood, muttering. "Bobo. Sixty percent. Hives." "That's the spirit. Now go practice your juggling." "I can't juggle." "Then Saturday is going to be very educational for you, isn't it?"
created_at
"2026-09-24T14:07:01.243Z"
9/24/2026, 2:07:01 PM
model
"aion-labs/aion-3.5-mini-20260923"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2830
moderation_latency
(null)
generation_time
47041
tokens_prompt
75
tokens_completion
1525
native_tokens_prompt
65
native_tokens_completion
1442
native_tokens_completion_images
(null)
native_tokens_reasoning
781
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
0.0020305
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1790258821-dgvzalL9QOmH0aFOtOV2"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790258821-J3acR19kctzhLupkbip2"
upstream_id
"a19fe06b2af3462db6a9d51471e48127"
provider_responses
0
endpoint_id
"60ac3bdc-90ec-4769-9193-2c00b4d79562"
id
"a19fe06b2af3462db6a9d51471e48127"
is_byok
false
latency
2823
model_permaslug
"aion-labs/aion-3.5-mini-20260923"
provider_name
"AionLabs"
status
200
total_cost
0.0020305
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
99.92%
Matches word count
n/a
neededClean
false
words
503
0.00%
Dialogue to Total Word Ratio
Ratio: 87.11%, Deviation: 17.11%
neededClean
false
wordsTotal
512
wordsDialogue
446
49.9595%