NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37PZKG5MS2RW6725B4N33TY
Run Details
Model:
Aion 3.5 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
6.9s
Cost:
$0.002161
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
60.28%
Matches word count
(details)
80.86%
Dialogue to Total Word Ratio
(details)
70.5683%
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 rented bouncy castle, adjusting the party hats she'd disguised herself with—three of them, stacked, because one hat was for amateurs. Bill wriggled up beside her dressed as a clown, though his makeup suggested a clown who had recently lost a custody battle. The backyard sprawled before them like a treasure map drawn by a sugar-crazed cartographer. A table groaned under a mountain of presents, wrapped in paper featuring cartoon dinosaurs and what appeared to be a duck wearing sunglasses. Somewhere, a piñata dangled, stuffed with candy and, if the birthday boy's wealthy grandmother was to be believed, several savings bonds. Bill consulted the laminated diagram he'd prepared. He had laminated everything. His sock was laminated. The diagram indicated a two-pronged approach: he would distract the children with his clown routine, while Molly loaded presents into the wagon she'd hidden under a tarp near the lemonade stand. "You look suspicious," she whispered. "I'm a clown." "Exactly." Their plan had one flaw, which they discovered simultaneously when the birthday boy approached, pointed at Bill, and announced to the entire party that this was not the clown his parents had hired. Bill froze mid-juggle. Molly, still wearing three party hats, began slowly backing toward the wagon, which a dog was now urinating on.
created_at
"2026-09-23T18:03:26.103Z"
9/23/2026, 6:03:26 PM
model
"aion-labs/aion-3.5-20260923"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
834
moderation_latency
(null)
generation_time
6871
tokens_prompt
75
tokens_completion
412
native_tokens_prompt
65
native_tokens_completion
352
native_tokens_completion_images
(null)
native_tokens_reasoning
68
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
0.00216075
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790186606-0XhsZseFMZdF1LG5yYxn"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790186606-ZUiJHF7x7wWl8Ud7Naby"
upstream_id
"a9cce0f44db14ad888f0b7bb7c9713b7"
provider_responses
0
endpoint_id
"09b1fc56-3888-42bd-b7a0-926851c7f9d6"
id
"a9cce0f44db14ad888f0b7bb7c9713b7"
is_byok
false
latency
834
model_permaslug
"aion-labs/aion-3.5-20260923"
provider_name
"AionLabs"
status
200
total_cost
0.00216075
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
60.28%
Matches word count
n/a
neededClean
false
words
215
80.86%
Dialogue to Total Word Ratio
Ratio: 3.21%, Deviation: 6.79%
neededClean
false
wordsTotal
218
wordsDialogue
7
70.5683%