NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37PRD6SDR9Z1BXZCFNZPR5R
Run Details
Model:
Aion 3.5 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
9.0s
Cost:
$0.002377
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
3.62%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
1.8117%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 rental van, binoculars in one hand, a map of the party venue in the other. The sound of screaming children and pop music drifted from the backyard. "Okay, Bill, here's the plan," she whispered. "You distract the clown. I'll hit the present table." Bill shook his head. "Absolutely not. Last time I distracted a clown, he made me a balloon animal. A balloon animal, Molly. It was a poodle. I still have it." "Oh, grow up. This is a seven-year-old's birthday party, not Fort Knox." "Exactly! There's a piñata. Do you know what happens when a piñata breaks? Chaos. Children are feral when candy is involved. We could get trampled." Molly studied the yard through her binoculars. "The presents are piled next to the cake table. Unguarded. It's almost insulting." "We're stealing from children," Bill said. "Have you no shame?" "Bill, we're thieves. Shame left the business plan around the same time you cried during A Bug's Life." "That was a heist movie for ants! Emotionally complex!" "Fine. New plan. I'll cut the power to the bounce house. When it deflates, we grab everything and run." Bill sighed, pulling a ski mask over his face. "A ski mask. At a birthday party. In July." "Commit to the bit, Bill." They crept toward the fence. Somewhere, a clown honked.
created_at
"2026-09-23T17:59:30.295Z"
9/23/2026, 5:59:30 PM
model
"aion-labs/aion-3.5-20260923"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
527
moderation_latency
(null)
generation_time
8881
tokens_prompt
75
tokens_completion
405
native_tokens_prompt
65
native_tokens_completion
388
native_tokens_completion_images
(null)
native_tokens_reasoning
70
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
0.00237675
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790186370-Dwh0030kHZV7HaOqWjKQ"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790186370-F34z5dQkUDsKja4zxxyG"
upstream_id
"5a3b48a553a04883adcd43f22542614d"
provider_responses
0
endpoint_id
"09b1fc56-3888-42bd-b7a0-926851c7f9d6"
id
"5a3b48a553a04883adcd43f22542614d"
is_byok
false
latency
527
model_permaslug
"aion-labs/aion-3.5-20260923"
provider_name
"AionLabs"
status
200
total_cost
0.00237675
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
3.62%
Matches word count
n/a
neededClean
false
words
224
0.00%
Dialogue to Total Word Ratio
Ratio: 70.80%, Deviation: 20.80%
neededClean
false
wordsTotal
226
wordsDialogue
160
1.8117%