NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37PKSJ419CFQ21Z3G9AEYDN
Run Details
Model:
Aion 3.5 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
8.9s
Cost:
$0.002731
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.95%
Dialogue to Total Word Ratio
(details)
99.9770%
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 peered through the binoculars. "Okay, there's the bouncy castle. There's the cake table. And there's the presents, right under the banner that says 'Happy Birthday, Timmy.'" "Perfect," Bill said, adjusting his clown wig. "I distract them with balloon animals. You stuff the presents in the piñata bag." "The piñata bag? Bill, the piñata is going to be hit with a bat. By children. Repeatedly." "That's the beauty of it. Nobody checks the piñata until the big moment." "That's not beauty, that's a design flaw." "Fine, use the cooler. Nobody looks in a cooler." "There are juice boxes in the cooler." "Then we steal those too. Diversify." Molly lowered the binoculars. "Have you considered that we're adults? That we could just... buy things?" Bill gasped. "That's not how we were raised." "We were raised by wolves, Bill." "Wolves with excellent heist instincts." "Fine. But if one more toddler hugs you and calls you Mr. Sprinkles, you're abandoning the mission again." "That was one time!" "You cried, Bill. You cried and gave the presents back and helped cut the cake." "It was a very emotional cake." "Get in the van." "It's a bouncy castle, actually." "Get in the bouncy castle."
created_at
"2026-09-23T17:56:59.092Z"
9/23/2026, 5:56:59 PM
model
"aion-labs/aion-3.5-20260923"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
647
moderation_latency
(null)
generation_time
8859
tokens_prompt
75
tokens_completion
476
native_tokens_prompt
65
native_tokens_completion
447
native_tokens_completion_images
(null)
native_tokens_reasoning
164
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
0.00273075
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790186219-zoBNdevyR7i22axrhY6F"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790186219-cADiD0o2paZw5DwYijOr"
upstream_id
"b137419590d44640841643f6725afc37"
provider_responses
0
endpoint_id
"09b1fc56-3888-42bd-b7a0-926851c7f9d6"
id
"b137419590d44640841643f6725afc37"
is_byok
false
latency
647
model_permaslug
"aion-labs/aion-3.5-20260923"
provider_name
"AionLabs"
status
200
total_cost
0.00273075
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
100.00%
Matches word count
n/a
neededClean
false
words
199
99.95%
Dialogue to Total Word Ratio
Ratio: 91.46%, Deviation: 1.46%
neededClean
false
wordsTotal
199
wordsDialogue
182
99.9770%