NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ74K9D5ZW9702YJ0888FFMN
Run Details
Model:
Qwen 3.6 35B
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
56.4s
Cost:
$0.009490
Provider:
AtlasCloud
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9581%
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 hissed, adjusting her ghillie suit woven from stolen gift ribbons while a stray helium balloon bumped against her shoulder. "Bill, focus. The security guard is a mom with a clipboard and terrifying judgment. Zip piñata. Cry if dropped." Bill nodded vigorously, checking his loot bag which was clearly a repurposed piñata filled with zip-ties and sheer greed. "I've got the distraction ready. The inflatable unicorn arrives at 4:02." Molly whispered urgently, frantically peering through a bubble wrap periscope made of duct tape and desperation. "Perfect timing. Kids mesmerized by the bouncing polyurethane disaster, we sprint for the tree." Bill asked nervously, frantically wiping sticky sweat and sprinkles from his forehead as the intoxicating scent of sugar rushed through the vent. "And the exit strategy?" Molly replied with a sharp aggressive motion, pointing a gloved finger toward the snack table where the real shimmering gold lay hidden beneath stacked paper plates. "Simple. We blend in. Nobody suspects the guy in the 'World's Best Uncle' mask to be looting a mountain of Play-Doh dinosaurs." "What if the birthday boy cries?" "Then you feed him a cupcake and keep moving. Forty minutes left before nap time ruins everything." "Let's roll. Leave the good wrapping paper."
created_at
"2026-04-27T09:33:46.283Z"
4/27/2026, 9:33:46 AM
model
"qwen/qwen3.6-35b-a3b-20260415"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
807
moderation_latency
(null)
generation_time
56313
tokens_prompt
77
tokens_completion
8096
native_tokens_prompt
76
native_tokens_completion
9819
native_tokens_completion_images
(null)
native_tokens_reasoning
9527
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
0.00949004
router
(null)
provider_responses
0
endpoint_id
"179c6985-3a1c-48f1-a009-9f3e3e402cdd"
id
"a40cfba86af540918cac02c4b70420e0"
is_byok
false
latency
807
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-1777282426-ESk7LQaiRfR4DLB4mGER"
session_id
(null)
api_type
"completions"
id
"gen-1777282426-H3Slln30pXm9ullg8M5J"
upstream_id
"a40cfba86af540918cac02c4b70420e0"
total_cost
0.00949004
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AtlasCloud"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
203
100.00%
Dialogue to Total Word Ratio
Ratio: 49.27%, Deviation: 0.73%
neededClean
false
wordsTotal
205
wordsDialogue
101
99.9581%