NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-07-01KWZ3GMH7VC7FRAP87ATHS46P
Run Details
Model:
Aion 3.0 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
13.5s
Cost:
$0.000791
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
18.3940%
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
“Alright, Bill, run it by me one more time. We’re hitting the ‘Pirate and Princess Pajama Jam.’” “Correct. The target is the gift table. Specifically, the ‘Cuddle-Me-Comet’ plush. It’s limited edition. Worth a fortune on the dark web.” “A fortune? From a kids’ party? Whose party is this, the mayor’s?” “Worse. It’s for Mr. Henderson’s kid. You know, the guy who owns the comic book store? He got a shipping crate of these things. The Hendersons are loaded. Their pool has a lazy river that’s just a giant Slip ‘N Slide.” “Right, right. So the plan. We’re the magician and the balloon animal lady. We have to look the part. I’m not jiggling in a sequined top, Bill. I have standards.” “Your standards are costing us the Cuddle-Me-Comet. I’ll be the magician. You do the animals. You can only make poodles. It’s fine.” “It is not fine. The kid wants a dragon. I give him a poodle. He cries. We get kicked out. Where’s the score?” “After the face painting, the parents get tipsy on the spiked punch. That’s our window. I’ll cause a distraction. I will ‘accidentally’ drop a bowling ball on the cake.” “You’re bringing a bowling ball to a kids’ party? In your magician costume?” “It’s my trick bowling ball. It squeaks. It’s adorable. Chaos will ensue. You grab the Comet and swap it with this ‘Glowy the Glowworm’ I got at a garage sale.” “Glowy the Glowworm? It looks like a used sock with googly eyes. That’s your decoy?” “It’s a vintage. The kids love the irony. Trust me. No one will notice the switch until the wrapping paper comes off.” “And what do we do when a dozen sugar-crazed pirates start asking for my poodles?” “We’ll be long gone. We just have to survive the limbo contest. I saw their party planner. She’s got a whistle and she’s not afraid to use it. Ready?” “I was born ready. I just wasn’t born in a sequined top.”
created_at
"2026-07-07T20:15:06.3Z"
7/7/2026, 8:15:06 PM
model
"aion-labs/aion-3.0-mini-20260707"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
576
moderation_latency
(null)
generation_time
13319
tokens_prompt
77
tokens_completion
546
native_tokens_prompt
66
native_tokens_completion
532
native_tokens_completion_images
(null)
native_tokens_reasoning
16
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
0.000791
router
(null)
provider_responses
0
endpoint_id
"0ad7ab68-a351-4a96-b2ef-fa8fe13adae3"
id
"54c05e3b0c94497fadcd7b8a659de938"
is_byok
false
latency
576
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-1783455306-tVhq3fAJlRkqSHz8XLRP"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783455306-xvt6JntuI07gcWAbi1fq"
upstream_id
"54c05e3b0c94497fadcd7b8a659de938"
total_cost
0.000791
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
0.00%
Matches word count
n/a
neededClean
false
words
331
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
334
wordsDialogue
334
18.3940%