NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37PWNPK5BPQF333FSSHSA1N
Run Details
Model:
Aion 3.5 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
37.6s
Cost:
$0.007147
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
97.55%
Dialogue to Total Word Ratio
(details)
98.4619%
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
"Tell me again why we're doing this," Bill said, adjusting his clown wig. "Because rich people buy rich presents, Bill. It's simple economics." "It's a seven-year-old's birthday party." "Precisely. Nobody suspects a clown at a child's party." "Everybody suspects a clown, Molly. Clowns are terrifying." "That's cultural bias. Now, you distract them with balloon animals while I load the van." "I can't make balloon animals." "Then you're a mime." "I'd rather be arrested than be a mime." "That can be arranged. Now listen, the presents go in the sack—" "We look like we're robbing Santa." "We ARE robbing Santa, Bill. We're just cutting out the middleman and the naughty list." "There will be children present. At the party. Watching us." "Which is why we're going through the garage." "The garage with the motion-sensor alarm?" "...The garage with the motion-sensor alarm," Molly admitted. "Did you plan any of this, or did you just see a bouncy castle and get greedy?" "Greedy people don't rent bouncy castles, Bill. They case them." "You rented one?" "For practice! Do you know how hard it is to walk in those things sober?" Bill stared at her. "Give me the wig."
created_at
"2026-09-23T18:01:50.06Z"
9/23/2026, 6:01:50 PM
model
"aion-labs/aion-3.5-20260923"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1059
moderation_latency
(null)
generation_time
37508
tokens_prompt
75
tokens_completion
1199
native_tokens_prompt
65
native_tokens_completion
1183
native_tokens_completion_images
(null)
native_tokens_reasoning
891
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
0.00714675
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790186510-eW2Y9UyAkmh88u5OL01c"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790186510-4hzQtl2dtvdxinZswqjx"
upstream_id
"ac0db70ab2684a03ae92386330ec2a72"
provider_responses
0
endpoint_id
"09b1fc56-3888-42bd-b7a0-926851c7f9d6"
id
"ac0db70ab2684a03ae92386330ec2a72"
is_byok
false
latency
1059
model_permaslug
"aion-labs/aion-3.5-20260923"
provider_name
"AionLabs"
status
200
total_cost
0.00714675
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
99.38%
Matches word count
n/a
neededClean
false
words
195
97.55%
Dialogue to Total Word Ratio
Ratio: 93.97%, Deviation: 3.97%
neededClean
false
wordsTotal
199
wordsDialogue
187
98.4619%