NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ746K5B9PW82TAG0AAMS25E
Run Details
Model:
Qwen 3.6 35B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 13s
Cost:
$0.011143
Provider:
AtlasCloud
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
99.78%
Dialogue to Total Word Ratio
(details)
98.7023%
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 peered through the crack in the patio door, her nose wrinkling at the scent of sugar and impending disaster. Beside her, Bill fumbled with a grappling hook made of twisted birthday ribbon, his hands shaking with the thrill of petty theft. He nearly knocked over a stack of wrapping paper, sending a cascade of glitter bombarding his boots. Molly hissed, adjusting her tinfoil helmet. She checked her watch, the timer ticking down to the dessert course. The window latch groaned under Bill's nervous weight, echoing through the silent suburban street like a dying whale. Bill whispered loudly, clutching his sack tightly. "The laser grid is just the streamers," Molly hissed, adjusting her tinfoil helmet. "You tripped over the piñata." "Piñatas are sharp." "Check the loot now?" "What if the parents intervene?" "We're in disguise. I'm a zombie accountant; you're a toaster." "Survive first, sulk later. The cake table is the vault. Once the kids nap, we grab the cache and vanish through the doggy door." "What if there's a guard dog?" "The dog is lazy. We have treats, you idiot." "Figure it out. Tonight we ride the rainbow of wealth. No books." "Can I keep the unicorn, pretty please?" "Only if we survive the bubble wrap."
created_at
"2026-04-27T09:26:50.288Z"
4/27/2026, 9:26:50 AM
model
"qwen/qwen3.6-35b-a3b-20260415"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
639
moderation_latency
(null)
generation_time
72944
tokens_prompt
77
tokens_completion
10287
native_tokens_prompt
76
native_tokens_completion
11531
native_tokens_completion_images
(null)
native_tokens_reasoning
11239
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"
usage
0.011142548
router
(null)
provider_responses
0
endpoint_id
"179c6985-3a1c-48f1-a009-9f3e3e402cdd"
id
"c38edbcea65b4b7f9427c13d6a5ab079"
is_byok
false
latency
639
model_permaslug
"qwen/qwen3.6-35b-a3b-20260415"
provider_name
"AtlasCloud"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777282010-MMfGsS6FoZIjzM60jWFy"
session_id
(null)
api_type
"completions"
id
"gen-1777282010-XVsVhim7o91SpiOdm5IU"
upstream_id
"c38edbcea65b4b7f9427c13d6a5ab079"
total_cost
0.011142548
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AtlasCloud"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
97.63%
Matches word count
n/a
neededClean
false
words
207
99.78%
Dialogue to Total Word Ratio
Ratio: 47.83%, Deviation: 2.17%
neededClean
false
wordsTotal
207
wordsDialogue
99
98.7023%