NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-07-01KWZ4HEDFQF1N166BSD669YGP
Run Details
Model:
Aion 3.0 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
27.3s
Cost:
$0.001364
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
6.09%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
21.4393%
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
“Okay, Bill, the target is the present table at the kids’ party.” “Presents from children, Molly. We’re stealing a toddler’s haul of plastic dinosaurs and coloring books.” “Don’t think of it as stealing. Think of it as redistribution. The GPS jammers are key.” “GPS jammers? For a party with a bouncy castle? What security?” “A laser tripwire around the cake and a hostile parent in a dinosaur costume. We neutralize the Dino.” “How? Offer him a napkin?” “I have a decoy gift. A Frozen karaoke machine. We swap it. He’ll be distracted for five minutes.” “You’re betting on Elsa beating a dinosaur?” “Exactly. You enter from the janitor’s closet. I create a diversion with a misplaced piñata. Grab the gifts, swap the decoys, and exit before the candles are blown.” “And if we’re caught?” “We’re the villains who ruined a birthday. Now put on this party hat. It’s camouflage.” “This is a paper cone with an elastic string.” “It’s tactical, Bill. The parents will see a fellow guest, not a thief.” “They’ll see two weirdos in adult-sized party hats.” “Then we’re very festive weirdos. Focus. The bounce house operator is our wildcard.” “I hate this plan.” “You hated the bank job, and that piggy bank was a clean score. Trust me. By the time the kids sing ‘Happy Birthday,’ we’ll be across town.”
created_at
"2026-07-07T20:33:01.374Z"
7/7/2026, 8:33:01 PM
model
"aion-labs/aion-3.0-mini-20260707"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
488
moderation_latency
(null)
generation_time
27183
tokens_prompt
77
tokens_completion
1044
native_tokens_prompt
66
native_tokens_completion
941
native_tokens_completion_images
(null)
native_tokens_reasoning
654
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
0.0013636
router
(null)
provider_responses
0
endpoint_id
"0ad7ab68-a351-4a96-b2ef-fa8fe13adae3"
id
"2d95b015b49d4df79d292e845f62ef1b"
is_byok
false
latency
488
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-1783456381-rcJ7Sor1lhIiibohgejp"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783456381-P9BYRsmlD1cbkTPcTukR"
upstream_id
"2d95b015b49d4df79d292e845f62ef1b"
total_cost
0.0013636
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
6.09%
Matches word count
n/a
neededClean
false
words
223
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
224
wordsDialogue
224
21.4393%