NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ78YGX3QQ858JNCCKMGEHS8
Run Details
Model:
Qwen 3.6 Flash
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
58.4s
Cost:
$0.017855
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
60.28%
Matches word count
(details)
11.44%
Dialogue to Total Word Ratio
(details)
35.8597%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 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 smoothed her camouflage jumpsuit, patterned with tiny bunnies to blend with the decor, and peered through the cardboard clown. The air reeked of sugar. "The payload is near the gingerbread house," she whispered, tapping her clipboard with a dirty pen. "Four hundred and fifty dollars in Legos and three tablets disguised as books." Bill twitched, his nose syncing with the disco ball. He clutched his utility belt, filled with contraband. "Volatile payload. One mismatched brick blows the plan. Distraction protocol? Timmy has the attention span of a caffeine-obsessed gnats." Molly flipped a page, her mind racing through escape routes and trajectory calculations of the play tube. "I've handled worse. This is a walk in the park, save for the parents, who bring clipboards and judgment." Bill swatted a ghost drifting past the bouncy castle, kicking a stray balloon as he wondered about inflating a distraction device. "So, wait for the cake?" "We strike during musical chairs," Molly declared, pointing a finger like a gun at the gyrating masses. Her voice carried the weight of a veteran thief who had once stolen a unicorn from a clown. "While they trip over shoelaces to 'Baby Shark', we bag the loot and replace it with expired fruit snacks. The confusion buys us thirty seconds to vanish through the play structure, assuming the net holds and the parents don't notice the gelatinous disappointment we leave behind." Bill rubbed his temples, visualizing the police response time, knowing local officers were too busy chasing a runaway ice cream truck to care about present snatching. "Three seconds, Molly. Parents have radar. We lost the diamond necklace because someone sneezed at a puppy. I need a contingency plan involving no animals or dental work." "Never bring the terrier to a heist," Molly hissed, leaning closer with the intensity of a hawk spotting a mouse. "This is 'The Great Present Purge'. Do you have the gags?" Bill produced a jingling velvet pouch, inspecting Swiss Army spoons and a yarn net with the reverence of a jeweler. "Helium and glitter. It blinds and hides the breach." Molly smiled, a spill of milk on a white carpet. "Magnificent. No eye contact. If Timmy asks if we're entertainment, we're the mime troupe until the fence." Confetti cannons fired, shaking dust from the rafters in a shower of paper snow. Molly dropped to one knee, signaling a halt. "Timing is tight," Bill whispered, checking his binary watch. "Ten minutes to piƱata fall. We move when it explodes, creating a candy cloud for cover." Molly's hand drifted to her groaning handbag, the bulges suggesting either electronics or a large sandwich. "And the fruit snacks?" Bill grimaced, his stomach rumbling with fear. "Always." He tightened his grip on the yarn net. Molly kicked the clown cutout and charged toward the snack table. Bill scrambled after her, a blur of nervous energy, leaving only the scent of juice and regret.
created_at
"2026-04-27T10:49:48.713Z"
4/27/2026, 10:49:48 AM
model
"qwen/qwen3.6-flash"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
645
moderation_latency
(null)
generation_time
58312
tokens_prompt
77
tokens_completion
11249
native_tokens_prompt
76
native_tokens_completion
11891
native_tokens_completion_images
(null)
native_tokens_reasoning
11224
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
0.0178555
router
(null)
provider_responses
0
endpoint_id
"2435bec9-c808-4f27-9fc8-12f3460d7b66"
id
"chatcmpl-27284999-32ff-9b53-8c96-a6fd3b4545f3"
is_byok
false
latency
645
model_permaslug
"qwen/qwen3.6-flash"
provider_name
"Alibaba"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777286988-K89F8b3ozfmgUq1ONDUc"
session_id
(null)
api_type
"completions"
id
"gen-1777286988-TEX0Q4dUaNqoRYQ28VVW"
upstream_id
"chatcmpl-27284999-32ff-9b53-8c96-a6fd3b4545f3"
total_cost
0.0178555
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
60.28%
Matches word count
n/a
neededClean
false
words
485
11.44%
Dialogue to Total Word Ratio
Ratio: 43.42%, Deviation: 6.58%
neededClean
false
wordsTotal
486
wordsDialogue
211
35.8597%