NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37PKW7FT8KH6MQP24M8FWFC
Run Details
Model:
Aion 3.5 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
16.9s
Cost:
$0.005029
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
86.38%
Matches word count
(details)
91.30%
Dialogue to Total Word Ratio
(details)
88.8393%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 a hedge shaped like a giraffe, binoculars pressed to her face, though the party was fifteen feet away. Through the window, she counted the presents stacked beneath a banner reading "Happy 6th Birthday, Timmy." "Twelve presents," she whispered. "Maybe thirteen." Bill, wedged beside her in a suit two sizes too small and a clown nose he refused to remove, consulted a laminated blueprint of the house he'd drawn himself in crayon. "The piñata is the wildcard," he muttered. The plan was elegant in its stupidity. They would enter through the back, disguised as entertainers Bill had "neutralized" that morning—a magician and, inexplicably, a second magician. Molly had argued for balloon artist, but Bill insisted the tuxedo was non-negotiable. Inside, sugar-crazed children shrieked like tiny sirens. A mother in a "Party Planner of the Year" apron guarded the gift table with the vigilance of a museum curator protecting the Mona Lisa. "Remember," Molly breathed, "we grab, we wrap, we vanish." Bill adjusted his squeaky nose. "What about the cake?" "We're professionals, Bill." He sighed, wounded. The cake was clearly the real prize, and Molly knew it. Somewhere in his heart, past three priors and a failed clown college application, he believed cake theft could be an art form.
created_at
"2026-09-23T17:57:01.826Z"
9/23/2026, 5:57:01 PM
model
"aion-labs/aion-3.5-20260923"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
591
moderation_latency
(null)
generation_time
16820
tokens_prompt
75
tokens_completion
873
native_tokens_prompt
65
native_tokens_completion
830
native_tokens_completion_images
(null)
native_tokens_reasoning
539
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
0.00502875
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790186221-Wr52L9M7nESiErba7sAJ"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790186221-cZWsZ6BdeZJHQXITtWce"
upstream_id
"b879bbdd958b4d0d9f380696d54b8d65"
provider_responses
0
endpoint_id
"09b1fc56-3888-42bd-b7a0-926851c7f9d6"
id
"b879bbdd958b4d0d9f380696d54b8d65"
is_byok
false
latency
588
model_permaslug
"aion-labs/aion-3.5-20260923"
provider_name
"AionLabs"
status
200
total_cost
0.00502875
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
86.38%
Matches word count
n/a
neededClean
false
words
211
91.30%
Dialogue to Total Word Ratio
Ratio: 15.49%, Deviation: 5.49%
neededClean
false
wordsTotal
213
wordsDialogue
33
88.8393%