NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8V4N55YZDJJ6Q0E8NK1KPH
Run Details
Model:
Aion 2.0
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
25.0s
Cost:
$0.001763
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
17.39%
Dialogue to Total Word Ratio
(details)
58.5695%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
The back booth of the diner was shrouded in coffee steam. Molly stirred her cup, staring at the napkin where Bill had drawn a crude map of a backyard. “Okay,” Bill said, tapping the napkin. “The target is a six-year-old named Timmy. His perimeter is soft, but the guards are hyper-vigilant.” “You mean his mom drinks a lot of iced tea and makes frequent trips inside,” Molly said flatly. “Precisely. That’s our window. We go in during the cake chaos. Everyone’s sugared up, distracted.” “To steal what? A pile of poorly wrapped Lego sets and a gift card to Chuck E. Cheese?” “It’s the principle, Moll. The score is the score. Now, extraction is key. We blend into the party, then exit via the side gate.” “Dressed as clowns? You said no clowns.” “Magicians. Higher tip potential on the way out. Look, the real prize is the giant stuffed panda from the grandparents. That’s the centerpiece. We need a vehicle with a large trunk.” Molly sipped her coffee. “I can’t believe I’m doing a five-year stretch for a panda that smells like grandma.” “Think of the secondary market,” Bill whispered. “The piñata alone is a goldmine.”
created_at
"2026-02-24T22:08:29.359Z"
2/24/2026, 10:08:29 PM
model
"aion-labs/aion-2.0-20260223"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2094
moderation_latency
(null)
generation_time
24979
tokens_prompt
77
tokens_completion
1106
native_tokens_prompt
170
native_tokens_completion
1017
native_tokens_completion_images
(null)
native_tokens_reasoning
788
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
0.0017632
router
(null)
provider_responses
0
endpoint_id
"1e93b0bb-eb0f-49bc-8fda-947105413b86"
id
"a6bb3891-655c-4e9c-ae53-4a3f8493d9c0"
is_byok
false
latency
126
model_permaslug
"aion-labs/aion-2.0-20260223"
provider_name
"AionLabs"
status
200
api_type
"completions"
id
"gen-1771970909-WBVB0BaEVTw2RoK97bMj"
upstream_id
"a6bb3891-655c-4e9c-ae53-4a3f8493d9c0"
total_cost
0.0017632
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AionLabs"
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
196
17.39%
Dialogue to Total Word Ratio
Ratio: 78.50%, Deviation: 11.50%
neededClean
false
wordsTotal
200
wordsDialogue
157
58.5695%