NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37P2PK7ZTFGSYCXQ0D739DA
Run Details
Model:
Aion 3.5 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
9.8s
Cost:
$0.002235
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
87.54%
Dialogue to Total Word Ratio
(details)
93.7628%
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
"Bill, this is a children's party. There will be clowns." "Clowns are just people, Molly." "Clowns are never just people." "Look, the intel says the birthday girl's getting a pony. A pony, Molly. Do you know what a pony fetches?" "Probably hay." "On the black market, you delightful menace. On the black market." "Fine. What's the plan?" "We go in as caterers." "We're wearing ski masks." "We'll take them off before we enter." "Then everyone sees our faces." "We put them back on after we're inside." "Bill, that's the worst sequence of decisions I've ever heard." "It's a sequence of decisions that ends with a pony." "Where are we even going to put a pony?" "The van." "The van we don't have." "The van I'm renting Tuesday." "It's Friday." "Details, Molly. Details. Look, we go in, we distract the kids, we grab the presents, we're out in six minutes." "How do you distract thirty children?" "I've been practicing balloon animals." "You have?" "Badly. That's the distraction. They'll gather around to mock me." "Bill, that's... actually not the worst sequence of decisions I've ever heard." "Thank you." "There's still the clown." "There's still the clown," he agreed grimly, pulling his mask back on.
created_at
"2026-09-23T17:47:38.999Z"
9/23/2026, 5:47:38 PM
model
"aion-labs/aion-3.5-20260923"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
963
moderation_latency
(null)
generation_time
9662
tokens_prompt
75
tokens_completion
376
native_tokens_prompt
65
native_tokens_completion
340
native_tokens_completion_images
(null)
native_tokens_reasoning
54
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
0.002235
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790185658-kkewGX7hrAmySIroMF47"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790185658-QapUgury10oS1oumfuo8"
upstream_id
"f9ea756c2def45f2aa6f52c2b2c75290"
provider_responses
0
endpoint_id
"09b1fc56-3888-42bd-b7a0-926851c7f9d6"
id
"f9ea756c2def45f2aa6f52c2b2c75290"
is_byok
false
latency
963
model_permaslug
"aion-labs/aion-3.5-20260923"
provider_name
"AionLabs"
status
200
total_cost
0.002235
cache_discount
(null)
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
99.98%
Matches word count
n/a
neededClean
false
words
202
87.54%
Dialogue to Total Word Ratio
Ratio: 96.04%, Deviation: 6.04%
neededClean
false
wordsTotal
202
wordsDialogue
194
93.7628%