NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8W9MZ0BR668CEX34FDWT9R
Run Details
Model:
Aion 2.0
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
26.0s
Cost:
$0.001678
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
6.09%
Matches word count
(details)
0.06%
Dialogue to Total Word Ratio
(details)
3.0743%
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
Molly traced a finger over the crayon-smeared invitation taped to the dashboard. “The target is a seven-year-old named Timmy. The party kicks off at two, piñata at three, cake at four. That’s our window.” Bill adjusted his binoculars, trained on the suburban backyard from their parked van. “Security?” “Lax. One adult male, designated ‘Dad,’ likely distracted by grill duties. One adult female, ‘Mom,’ on juice-box distribution. The real variable is the target’s older sister, Jessica. Thirteen. She’s been on her phone for forty minutes, but she’s unpredictable.” “We need a distraction. Classic misdirection.” Bill tapped his chin. “I could trigger a small, contained grease fire at the grill.” “Or,” Molly said, pulling a garish, rainbow-colored wig from a bag, “I could be ‘Auntie Shimmer,’ a last-minute guest from out of town, tragically allergic to cake frosting. I’ll cause a scene near the dessert table. You, in the catering uniform we lifted, go for the presents. They’re stacked by the sliding door.” “Catering uniform? It’s a polo shirt with a dinosaur on it, Mol.” “It’s a uniform of the establishment. Blend. Now, extraction?” Bill pointed to the side gate. “Through the neighbor’s yard. Their dog is a non-issue. I’ve been feeding him sausages all week. He thinks I’m his best friend.” “You corrupted a Labrador?” “It’s asset acquisition. Back to the loot. What’s the estimated haul?” Molly consulted a notepad. “Based on registry intel and standard gift-spend for this demographic, we’re looking at twelve to fifteen units. Mostly plastic, some electronic. A couple of ‘experience’ gifts, which are worthless. One confirmed high-value item: a ‘Super Spy Ultimate Watch.’ Retail eighty bucks.” Bill whistled. “The big score. Alright. Contingencies?” “If ‘Dad’ gets heroic, hit him with the squirt gun full of ranch dressing. It’s non-lethal and deeply confusing. If Jessica becomes actively hostile, deploy the glitter bomb. It’s a psychological retreat we developed for mall security.” “Glitter bomb. Nice.” Bill nodded, then his face fell. “Wait. What about the piñata?” “What about it?” “It’s a classic diversionary tactic! A swarm of sugar-crazed minors scrambling for candy. We could use that chaos. Maybe I swing in, grab the presents while they’re all looking at the broken donkey.” Molly stared at him. “You want to alter a meticulously timed plan for a piñata?” “It’s a strategic opportunity!” “It’s a papier-mâché donkey filled with Tootsie Rolls. Stay on mission. The cake meltdown is cleaner.” She checked her watch. “We go in ninety minutes. Synchronize.” Bill sighed, lifting a tiny, earpiece. “Testing. Can you hear me?” “I’m sitting right next to you, Bill.” “Just protocol. Final question: what’s our cover if we’re made?” Molly handed him a small, wrapped box. “We’re just two overly enthusiastic guests who got the date wrong. We brought a gift.” Bill shook the box. It rattled softly. “What’s in it?” “A dozen of those sausages. For the dog.”
created_at
"2026-02-24T22:28:41.578Z"
2/24/2026, 10:28:41 PM
model
"aion-labs/aion-2.0-20260223"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2065
moderation_latency
(null)
generation_time
25923
tokens_prompt
77
tokens_completion
1110
native_tokens_prompt
170
native_tokens_completion
964
native_tokens_completion_images
(null)
native_tokens_reasoning
247
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.0016784
router
(null)
provider_responses
0
endpoint_id
"1e93b0bb-eb0f-49bc-8fda-947105413b86"
id
"a2b9e10e-0973-4d6a-b029-b341c3d6be2a"
is_byok
false
latency
118
model_permaslug
"aion-labs/aion-2.0-20260223"
provider_name
"AionLabs"
status
200
api_type
"completions"
id
"gen-1771972121-1PgLdGYibEcD6ZcdAPlo"
upstream_id
"a2b9e10e-0973-4d6a-b029-b341c3d6be2a"
total_cost
0.0016784
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AionLabs"
Evaluation details
Result
Evaluator
Details
Meta Data
6.09%
Matches word count
n/a
neededClean
false
words
477
0.06%
Dialogue to Total Word Ratio
Ratio: 82.21%, Deviation: 12.21%
neededClean
false
wordsTotal
489
wordsDialogue
402
3.0743%