NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37P34KSDFWEX3TRT0K11VK3
Run Details
Model:
Aion 3.5 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
20.4s
Cost:
$0.004227
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9920%
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, binoculars pressed to her face. "There. The gift table. Forty-two presents, give or take a Barbie." Bill tugged at his costume and sighed. "I still don't understand why I have to be the elf." "Because I'm already the clown, Bill. One of us has to look festive." "I look like a pointy-eared hobo." "That's just what elves look like. It's canon." Molly peered around the corner, watching the chaos unfold. "Okay, the piƱata breaks at three. When those kids stampede for candy, we grab the gifts and walk out through the kitchen." Bill frowned. "And if a kid sees us?" "Then you do the elf magic thing." "That's not a real thing, Molly." "Everything's real if you say it with confidence. Rule one of theft." Bill shifted his tights uncomfortably. "What if the parents want a photo with us?" "Then you smile, wave, and keep pocketing the loot. We're thieves, not monsters." "I joined this crew to steal diamonds, not juice boxes." "And yet here we are, casing a six-year-old's birthday party. Dreams evolve, Bill." "I want it noted that I hate this." "Noted. Now grab that teddy bear and act jolly."
created_at
"2026-09-23T17:47:53.353Z"
9/23/2026, 5:47:53 PM
model
"aion-labs/aion-3.5-20260923"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1172
moderation_latency
(null)
generation_time
20377
tokens_prompt
75
tokens_completion
711
native_tokens_prompt
65
native_tokens_completion
672
native_tokens_completion_images
(null)
native_tokens_reasoning
415
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
0.004227
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790185673-P1MEC8jzhzCiXSLqocBn"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790185673-b8fc6PV5f06p4pOwItOH"
upstream_id
"82c794e61de641beb9f53dc5658b864e"
provider_responses
0
endpoint_id
"09b1fc56-3888-42bd-b7a0-926851c7f9d6"
id
"82c794e61de641beb9f53dc5658b864e"
is_byok
false
latency
1170
model_permaslug
"aion-labs/aion-3.5-20260923"
provider_name
"AionLabs"
status
200
total_cost
0.004227
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
198
0.00%
Dialogue to Total Word Ratio
Ratio: 83.17%, Deviation: 33.17%
neededClean
false
wordsTotal
202
wordsDialogue
168
49.9920%