NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37PYCAEYW8RYN65XHM0CR8H
Run Details
Model:
Aion 3.5 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
21.9s
Cost:
$0.004801
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
43.38%
Matches word count
(details)
99.97%
Dialogue to Total Word Ratio
(details)
71.6756%
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 the bouncy castle, binoculars pressed to her face, though the party was only fifteen feet away. Bill lay beside her in what he insisted was tactical gear but was unmistakably a burgundy tracksuit from a discount bin. "Any guards?" Bill whispered. "One clown. Asleep. Drooling on his bow tie." Molly adjusted her binoculars. "Presents are stacked by the piƱata." Bill nodded with the gravity of a man who had once stolen a lawn flamingo and never let anyone forget it. They had spent three weeks planning this job. There was a laminated diagram. There was a color-coded timeline. There was, inexplicably, a decoy balloon. The plan was elegant in its simplicity: enter through the hedge, pose as Aunt Carol and her husband Gary, load the presents into a wagon disguised as a stroller, and vanish before the cake was cut. Molly signaled. Bill rolled through the hedge with all the stealth of a filing cabinet falling downstairs. The clown stirred but did not wake. They crept toward the pile. Teddy bears, board games, something that beeped ominously. Bill reached for a wrapped box, and a child of about six looked up at him with enormous, unblinking eyes. "Gary?" the child said. "You came!" Bill froze. Molly sighed. The plan had not accounted for recognition.
created_at
"2026-09-23T18:02:45.983Z"
9/23/2026, 6:02:45 PM
model
"aion-labs/aion-3.5-20260923"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
850
moderation_latency
(null)
generation_time
21828
tokens_prompt
75
tokens_completion
838
native_tokens_prompt
65
native_tokens_completion
792
native_tokens_completion_images
(null)
native_tokens_reasoning
510
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
0.00480075
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790186565-ucIrImpCA2paoNPUveqi"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790186565-TMLChhtNiOKifiL2yTCn"
upstream_id
"f1237d1173b54cd3b179d283ffeaa9e7"
provider_responses
0
endpoint_id
"09b1fc56-3888-42bd-b7a0-926851c7f9d6"
id
"f1237d1173b54cd3b179d283ffeaa9e7"
is_byok
false
latency
850
model_permaslug
"aion-labs/aion-3.5-20260923"
provider_name
"AionLabs"
status
200
total_cost
0.00480075
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
43.38%
Matches word count
n/a
neededClean
false
words
217
99.97%
Dialogue to Total Word Ratio
Ratio: 8.72%, Deviation: 1.28%
neededClean
false
wordsTotal
218
wordsDialogue
19
71.6756%