NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-24-01M39W6JZZQYZZ81MZS38FYJJP
Run Details
Model:
Aion 3.5 Mini (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
38.1s
Cost:
$0.002487
Provider:
AionLabs
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
86.05%
Dialogue to Total Word Ratio
(details)
89.8474%
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
Bill spread the blueprints across the diner table. "Okay, so the target is a seven-year-old's birthday party." "Whose?" "Little Timmy Fenwick. Rich family, Molly. Loaded." "And the presents?" "Wrapped, stacked by the bounce house, completely unguarded." "There's a clown, Bill." "One clown. I can take one clown." "You cried at the circus in 2019." "That clown owed me money. Different situation. I've got a plan. During musical chairs, you cut the power—" "It's a backyard. The music's a Bluetooth speaker." "Then you distract the parents. I grab the loot, we're gone in ninety seconds." "What about the birthday boy?" "Timmy gets cake, we get presents. Everybody wins." "Everybody except Timmy." "Details. What's the extraction route?" "The bounce house. We deflate it, crawl out under the fence." "You want to escape through a bounce house." "It's the last place they'll look." "Because it's insane, Bill." "Fine. Plan B. I put on the clown nose—" "You are not becoming the clown." "Then how do we get past the piñata?" "The what?" "Security piñata. Candy-filled alarm system. Kids whack it, sensor triggers." "You're making that up." "Am I? Then explain why the invitation says 'no piñata smashers after dark.'" "Fine. We whack it together. For the job." "Now that's the heist spirit."
created_at
"2026-09-24T14:13:06.7Z"
9/24/2026, 2:13:06 PM
model
"aion-labs/aion-3.5-mini-20260923"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2521
moderation_latency
(null)
generation_time
38064
tokens_prompt
75
tokens_completion
1660
native_tokens_prompt
65
native_tokens_completion
1768
native_tokens_completion_images
(null)
native_tokens_reasoning
1314
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
0.0024869
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1790259186-SrBjqumSYbDlo8iTIZog"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790259186-QnsPdZ9aLIrmNG6ixEiA"
upstream_id
"79362fac2b0a4c8fa37c7a6f518be17b"
provider_responses
0
endpoint_id
"60ac3bdc-90ec-4769-9193-2c00b4d79562"
id
"79362fac2b0a4c8fa37c7a6f518be17b"
is_byok
false
latency
2521
model_permaslug
"aion-labs/aion-3.5-mini-20260923"
provider_name
"AionLabs"
status
200
total_cost
0.0024869
cache_discount
0.0000338
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
86.05%
Dialogue to Total Word Ratio
Ratio: 96.23%, Deviation: 6.23%
neededClean
false
wordsTotal
212
wordsDialogue
204
89.8474%