NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37Q59ZBWEWQ6W5HST4BFJDK
Run Details
Model:
Aion 3.5 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 22s
Cost:
$0.016411
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
96.8243%
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 of plastic flamingos, studying the backyard through binoculars. The target: a princess-themed birthday party, complete with bouncy castle and thirty-odd presents stacked on a picnic table like a pirate's ransom. Bill scribbled notes in a tiny notebook, tongue poking out in concentration. He'd drawn a map that bore no resemblance to reality whatsoever. The plan was elegant in its stupidity. Molly would pose as the entertainment, wearing a clown costume that smelled faintly of regret and old bologna. Bill would handle extraction, filling a trash bag labeled "recycling" with gift-wrapped treasure. "You look ridiculous," Bill muttered. "It's tactical camouflage, obviously," Molly hissed, adjusting her rainbow wig. They'd rehearsed for weeks. Bill had practiced juggling with oranges until the fruit court issued a restraining order. Molly had perfected a balloon animal resembling either a giraffe or a tragic accident. Inside, children shrieked with joy, blissfully unaware that two adults with the combined stealth of a marching band were about to ruin everything. Molly took a deep breath. "Remember, we're professionals." Bill nodded solemnly, then tripped over a garden gnome. "I hate clowns," he whispered from the ground. "Operation Party Pooper is a go," Molly whispered. Bill saluted, knocking his fake mustache into the punch bowl.
created_at
"2026-09-23T18:06:32.957Z"
9/23/2026, 6:06:32 PM
model
"aion-labs/aion-3.5-20260923"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1451
moderation_latency
(null)
generation_time
82286
tokens_prompt
75
tokens_completion
2542
native_tokens_prompt
65
native_tokens_completion
2727
native_tokens_completion_images
(null)
native_tokens_reasoning
2188
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
0.01641075
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790186792-IRfg8qGhCI55zbU0ttkA"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790186792-m9L7FVFc0zxW1ghjCiYq"
upstream_id
"38b0bee1a38f42ad9d3eda1c506db5e2"
provider_responses
0
endpoint_id
"09b1fc56-3888-42bd-b7a0-926851c7f9d6"
id
"38b0bee1a38f42ad9d3eda1c506db5e2"
is_byok
false
latency
1451
model_permaslug
"aion-labs/aion-3.5-20260923"
provider_name
"AionLabs"
status
200
total_cost
0.01641075
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
93.65%
Matches word count
n/a
neededClean
false
words
209
100.00%
Dialogue to Total Word Ratio
Ratio: 9.43%, Deviation: 0.57%
neededClean
false
wordsTotal
212
wordsDialogue
20
96.8243%