NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37NXME10V3PS1X7VZHN750Q
Run Details
Model:
Aion 3.5 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
19.7s
Cost:
$0.005035
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 70% 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 inflatable bouncy castle, binoculars pressed to her face, while Bill stood beside her jingling the car keys. "Bill, put the keys away. You're going to give us away." "Give us away? Molly, we're hiding behind a giant purple dinosaur at a seven-year-old's birthday party. I think the keys are the least of our problems." "Fine, but if you jingle those things one more time, I'm feeding them to the clown." "There's a clown?" "There's always a clown, Bill. That's rule number one of party heists. Scope out the clown." Bill peered over the bouncy castle. "He's making a balloon poodle. Okay, so what's the plan? We grab the presents, we run, we fence them to... who exactly? Who buys stolen presents?" "Grandparents who forgot to buy anything. It's a booming market. Now listen. The presents are stacked on the table next to the cake. I'll create a diversion, and you grab them." "Why are you the diversion? Last time you were the diversion, you ended up in a dance-off with a retiree." "That was a casino, Bill. Different venue, different rules. This time I'm going to release the piñata." "Release it? It's not an animal, Molly. It's paper and candy." "It's a donkey, Bill. A paper donkey full of candy, and when I pull that string, children will descend on it like sharks. Chaos. Beautiful, sugary chaos. And while they're fighting over the candy corn, you load the presents into the van." "The van? We brought the van that says 'Free Candy' on the side?" "It's a party van! It's thematic! It blends in!" "It says Free Candy, Molly. At a children's party. That's not blending in, that's a public safety announcement." "Fine. Fine. We'll move the van around back. But the plan stands. Piñata chaos, present grab, gone in ninety seconds." Bill rubbed his chin. "What about the parents?" "What about them?" "There's like twelve of them, and they're all drinking coffee and judging each other. One of them will notice a grown man stuffing a My Little Pony castle into a duffel bag." "That's why you're wearing the caterer's uniform." "I'm wearing a paper hat, Molly. A paper hat does not make me a caterer." "It makes you plausible. Plausible is all we need. Now, is the duffel bag big enough?" "It's enormous. I could fit a golden retriever in this thing." "Great. Okay. On my signal, I release the piñata. You go for the table. Meet at the van in ninety seconds." "What's the signal?" "I'll whistle." "You can't whistle. You've never been able to whistle. At our wedding, you tried to whistle for the car and a pigeon landed on your head." "I've been practicing. It's fine." "Molly." "Bill." "I'm just saying, maybe the signal should be something else." "Fine. The signal is I yell 'Fire!'" "You're going to yell fire at a children's birthday party?" "Okay, the signal is I yell 'Cake time!'" "That's better. That's actually not bad." "Thank you. Now put on your paper hat, Bill. We're going in." Bill adjusted the hat solemnly. "For the record, I think this is our worst plan ever." "You said that about the zoo job." "The flamingo is still in our garage, Molly." "He's family now. Positions, everyone. Cake time in three, two, one—"
created_at
"2026-09-23T17:44:52.946Z"
9/23/2026, 5:44:52 PM
model
"aion-labs/aion-3.5-20260923"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
651
moderation_latency
(null)
generation_time
19651
tokens_prompt
75
tokens_completion
881
native_tokens_prompt
65
native_tokens_completion
831
native_tokens_completion_images
(null)
native_tokens_reasoning
60
native_tokens_cached
65
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
0.00503475
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790185492-TAdL4RTZ5Z3vBS2Fn6uL"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790185492-iF7aAqaxQ0JnKyz7azYp"
upstream_id
"4e1a2873c62b4815bd4396dbaa3c14a3"
provider_responses
0
endpoint_id
"09b1fc56-3888-42bd-b7a0-926851c7f9d6"
id
"4e1a2873c62b4815bd4396dbaa3c14a3"
is_byok
false
latency
651
model_permaslug
"aion-labs/aion-3.5-20260923"
provider_name
"AionLabs"
status
200
total_cost
0.00503475
cache_discount
0.00014625
upstream_inference_cost
0
provider_name
"AionLabs"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
552
0.00%
Dialogue to Total Word Ratio
Ratio: 93.51%, Deviation: 23.51%
neededClean
false
wordsTotal
555
wordsDialogue
519
0.0000%