NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ7A0AD3QTVK5PD7KNVAQKR8
Run Details
Model:
Qwen3.6 Max Preview
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
3m 43s
Cost:
$0.065127
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 30% 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
The blueprint was drawn in crayon on the back of a pizza coupon. Molly smoothed the wrinkled paper with a calloused palm while Bill adjusted his night vision goggles, which were currently pointed at a potted fern. The safe house smelled of lemon pledge and stolen garden gnomes. On the table sat three juice boxes, a half eaten bag of animal crackers, and a detailed schematic of a bouncy castle marked with tactical entry points. Molly studied the wax markings like a general surveying a battlefield. She traced the perimeter fence with a burnt matchstick, calculating wind speed and toddler migration patterns. Bill shifted his weight, his tactical knee pads squeaking against the linoleum. The tension was thick enough to spread on toast. Molly unrolled a velvet cloth revealing their specialized equipment. There were garden shears modified for ribbon cutting, a grappling hook fashioned from a repurposed candy cane, and two pairs of slippers designed for maximum stealth on hardwood floors. She polished a suction cup with microscopic dedication. The neighborhood outside remained blissfully unaware. Lawn sprinklers oscillated in gentle arcs. A distant ice cream truck played its haunting melody, signaling the approach of zero hour. Bill loaded a tranquilizer dart into a modified bubble wand. He practiced his breathing exercises, inhaling through his nose and exhaling through his mouth like a yogi preparing for war. The stakes were astronomical. One wrong step and they would face the ultimate consequence. We go in during musical chairs. The parents will be comatose from potato salad. Bill adjusted his velvet glove. What about the hired clown? Neutralized. I bribed him with a bus ticket. We have four minutes before piƱata deployment. Bill squinted at the arrows. The wrapping paper crinkles. We need silent bags. Already sourced. Totes lined with foam. I tested them on a holiday ham. He rubbed his chin. You thought of everything. Even the goodie bags? Decoys. Filled with raisins. Keeps the hostages occupied during extraction. Bill paced the floor. I will handle the perimeter. The golden retriever knows fear. Molly slid a container forward. Kibble with melatonin. Freeze and they think you are furniture. Bill holstered his tape dispenser. I feel ready. Big league stuff. Keep your shoes tied. Do not touch the cake. Fondant is a trap. He saluted. Understood. Operation Sugar Rush is a go. Molly rolled up the crayon blueprint and tucked it into her tactical fanny pack. The microwave clock blinked twelve forty seven. Somewhere across town, a magician was practicing card tricks for an audience that would soon be missing every building block set in the neighborhood. She checked her watch, adjusted her elbow pads, and prayed the inflatable castle held its air long enough for a clean getaway. She double checked the zip ties and calibrated the walkie talkies to channel four. Dust motes danced in the slanted afternoon light, completely indifferent to the criminal enterprise unfolding beneath them. Bill tightened his utility belt, which held nothing but wet wipes and a spare pacifier for emergency negotiations. The game was afoot. The presents were waiting. Failure was not an option, mostly because the return policy at the toy store was notoriously strict. They moved toward the door, shadows in a suburb that never suspected a thing.
created_at
"2026-04-27T11:08:16.169Z"
4/27/2026, 11:08:16 AM
model
"qwen/qwen3.6-max-preview-20260420"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1084
moderation_latency
(null)
generation_time
222617
tokens_prompt
77
tokens_completion
8710
native_tokens_prompt
76
native_tokens_completion
8337
native_tokens_completion_images
(null)
native_tokens_reasoning
7638
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
0.0651274
router
(null)
provider_responses
0
endpoint_id
"ca7fc0c7-f23d-4ac5-b2e0-945be5b61787"
id
"chatcmpl-4960d820-64ab-9da6-88fd-8f2dfbf9a534"
is_byok
false
latency
1084
model_permaslug
"qwen/qwen3.6-max-preview-20260420"
provider_name
"Alibaba"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777288096-h1pIdnTHBl9ynRvdb19y"
session_id
(null)
api_type
"completions"
id
"gen-1777288096-ah3q3U3wxPiyhLciQq0Y"
upstream_id
"chatcmpl-4960d820-64ab-9da6-88fd-8f2dfbf9a534"
total_cost
0.0651274
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
544
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 30.00%
neededClean
false
wordsTotal
544
wordsDialogue
0
0.0000%