NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-07-01KWZ31S8FN5CFAZVWG9JD8F1E
Run Details
Model:
Aion 3.0 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
59.3s
Cost:
$0.002790
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
51.93%
Matches word count
(details)
80.86%
Dialogue to Total Word Ratio
(details)
66.3935%
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
Molly crouched behind the hedge. "Okay, the target is a fortress. A fortress of glitter and screaming." Bill squinted. "It's a seven-year-old's birthday party, Moll. Not the Pentagon." "The Pentagon doesn't have a magician who can turn security guards into doves. See that guy with the wand? He's a variable." "He's a stoned college kid in a polyester tux. My grandmother could take him." "Your grandmother is dead, Bill." "Exactly. My point stands. Look, the real problem is the loot. The presents are under a giant cardboard castle. We sneak in as waitstaff, grab the pile, and exit via the cake table. Distraction is the piñata." "You want to use a piñata as a diversion? For a heist? That's your masterstroke?" "It's a big donkey. It's full of candy. Kids love it. One whack and chaos ensues. We walk out with the haul." "And if the birthday girl cries?" "Then we feel bad. But rich. Mostly rich." "Fine. But I'm keeping the good toys. That unicorn plushie looks premium. It's going in my vault." "Deal. But I get the gift cards. And the fruit basket." "You're a monster. You'd take fruit from a child?" "I'm a professional. The fruit basket is a classic misdirection. They'll be looking for the missing toys, not the missing Granny Smiths."
created_at
"2026-07-07T20:06:59.614Z"
7/7/2026, 8:06:59 PM
model
"aion-labs/aion-3.0-mini-20260707"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
740
moderation_latency
(null)
generation_time
59171
tokens_prompt
77
tokens_completion
2049
native_tokens_prompt
66
native_tokens_completion
1960
native_tokens_completion_images
(null)
native_tokens_reasoning
1713
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
0.0027902
router
(null)
provider_responses
0
endpoint_id
"0ad7ab68-a351-4a96-b2ef-fa8fe13adae3"
id
"f672fbf63570424aab251776d23847ce"
is_byok
false
latency
740
model_permaslug
"aion-labs/aion-3.0-mini-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-1783454819-A9SxgmW6gfFGrCpLqoa1"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783454819-txRG5N8dior0a57KFLjS"
upstream_id
"f672fbf63570424aab251776d23847ce"
total_cost
0.0027902
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
51.93%
Matches word count
n/a
neededClean
false
words
216
80.86%
Dialogue to Total Word Ratio
Ratio: 96.79%, Deviation: 6.79%
neededClean
false
wordsTotal
218
wordsDialogue
211
66.3935%