NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-07-01KWZ3R4Z9S1G3PRAMS93A93TY
Run Details
Model:
Aion 3.0
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
6.4s
Cost:
$0.002289
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
53.88%
Dialogue to Total Word Ratio
(details)
73.7644%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 oversized sunglasses in the rearview mirror, scanning the suburban cul-de-sac where pastel balloons marked their target. She had been planning this job for three weeks, mapping the rotation of bored parents, the shift change of the birthday clown, and the precise moment when the piƱata would burst and chaos would reign. "Remember, you're the uncle nobody invited," she reminded Bill, who was struggling with a Hawaiian shirt two sizes too small. The polyester stretched across his belly like a drum skin, and the pineapples on the pattern seemed to warp with each breath he took. Bill scratched his stubble, eyeing the bounce house with suspicion. "What if someone asks me to do magic tricks?" "Then you'll disappoint them like every other adult in their lives," Molly said. "Now help me with the van." They moved quickly, unloading empty gift bags and a portable speaker pre-loaded with crying baby sound effects. The plan was simple: create a distraction near the dessert table, bag the loot from the gift pile, and slip out before the sugar crash hit the under-ten demographic. Bill paused, watching a toddler waddle past with a juice box. "This feels wrong." Molly shoved a gift bag into his chest. "That's your conscience. Ignore it."
created_at
"2026-07-07T20:19:12.508Z"
7/7/2026, 8:19:12 PM
model
"aion-labs/aion-3.0-20260707"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
713
moderation_latency
(null)
generation_time
6188
tokens_prompt
77
tokens_completion
413
native_tokens_prompt
67
native_tokens_completion
348
native_tokens_completion_images
(null)
native_tokens_reasoning
86
native_tokens_cached
0
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
0.002289
router
(null)
provider_responses
0
endpoint_id
"8c8f827d-2bef-468a-8f9e-8e27b470de5e"
id
"49f8ccd43e0347b7b73c8cd003875be3"
is_byok
false
latency
713
model_permaslug
"aion-labs/aion-3.0-20260707"
provider_name
"AionLabs"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1783455552-1L3nULNteN9QpACN1NGa"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783455552-I8okl3deCwKdOD84yZuv"
upstream_id
"49f8ccd43e0347b7b73c8cd003875be3"
total_cost
0.002289
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AionLabs"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
93.65%
Matches word count
n/a
neededClean
false
words
209
53.88%
Dialogue to Total Word Ratio
Ratio: 18.87%, Deviation: 8.87%
neededClean
false
wordsTotal
212
wordsDialogue
40
73.7644%