NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8W280XJF451BEE6NDYZJ59
Run Details
Model:
Aion 2.0
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
26.4s
Cost:
$0.001869
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
46.87%
Dialogue to Total Word Ratio
(details)
72.7911%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 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 adjusted her black beanie, flattening it over her eyebrows as she studied the crayon-smeared map taped to the diner table. Bill peered over her shoulder, his finger tracing a route through a carefully drawn diagram of a bouncy castle. "The target is a fortified suburban ranch," Molly whispered, ignoring the smell of stale pancakes. "Perimeter is soft, but crawling with short, sugar-fueled hostiles." Bill nodded, adjusting his unconvincing fake mustache. "Intel confirms the loot is concentrated in the 'gift nook' near the piƱata. Our window is during the 'musical statues' distraction. Chaos theory at its finest." "Extraction route?" "Through the hydrangea hedge, into the getaway wagon." He gestured vaguely toward the window, where a battered ice cream truck idled. "But Molly, the big variable... the birthday boy's dog. A Yorkshire Terrier named Mr. Snuffles. He's a known ankle-biter." Molly sighed, rubbing her temples. "I'll bring extra socks. Now, the real question: do we grab the goody bags on the way out?" Bill looked offended. "Only if we have time. We're thieves, not monsters. Professionalism, Molly. This is a precision operation." He paused, frowning. "You did remember to RSVP as 'Clown Cousin Larry,' right?" "Relax," Molly said, folding the map. "My balloon animal skills are... passable."
created_at
"2026-02-24T22:24:38.951Z"
2/24/2026, 10:24:38 PM
model
"aion-labs/aion-2.0-20260223"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1667
moderation_latency
(null)
generation_time
26298
tokens_prompt
77
tokens_completion
1197
native_tokens_prompt
170
native_tokens_completion
1083
native_tokens_completion_images
(null)
native_tokens_reasoning
853
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
0.0018688
router
(null)
provider_responses
0
endpoint_id
"1e93b0bb-eb0f-49bc-8fda-947105413b86"
id
"e9b0540f-fe3e-4da1-ac9a-eff0c3a9f05e"
is_byok
false
latency
117
model_permaslug
"aion-labs/aion-2.0-20260223"
provider_name
"AionLabs"
status
200
api_type
"completions"
id
"gen-1771971878-0ey2ac5rKJUKnG06zvOt"
upstream_id
"e9b0540f-fe3e-4da1-ac9a-eff0c3a9f05e"
total_cost
0.0018688
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AionLabs"
Evaluation details
Result
Evaluator
Details
Meta Data
98.71%
Matches word count
n/a
neededClean
false
words
206
46.87%
Dialogue to Total Word Ratio
Ratio: 59.33%, Deviation: 9.33%
neededClean
false
wordsTotal
209
wordsDialogue
124
72.7911%