NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ78TQYX2FV61FGTHM53P1PN
Run Details
Model:
Qwen3.6 Max Preview
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
4m 37s
Cost:
$0.079277
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
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 smoothed the wrinkled crayon map across the sticky booth surface. "We enter during the magic act." Bill adjusted his tight leather gloves and examined the drawing closely. "What about the parents?" Molly tapped the illustrated wooden fence with sudden confidence. "They will be distracted by gossip. We crawl under the trampoline, snatch the presents, and escape before the piƱata drops." Bill sipped his bitter lukewarm tea and frowned deeply today. "Children are observant. They scream loudly." Molly checked her stolen silver watch and calculated carefully again. "Not after the sugar crash hits. I studied the schedule. Four o'clock guarantees total naps. We wear giant floppy shoes for cover." Bill drummed his anxious fingers nervously against the table wood. "I hate floppy shoes. They squeak loudly." Molly packed the large empty duffel bag with steady precision. "Then walk carefully. The prize is enormous. Vintage games, thick envelopes, maybe a laptop." Bill rubbed his sore aching temples and sighed heavily. "Fine. But if one toddler wakes, I am running away fast." Molly slid a plastic red nose forward across the table. "Just watch my signal. When the balloon pops, we bolt." Bill pocketed the cheap foam disguise and stood up slowly.
created_at
"2026-04-27T10:47:44.868Z"
4/27/2026, 10:47:44 AM
model
"qwen/qwen3.6-max-preview-20260420"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1372
moderation_latency
(null)
generation_time
276773
tokens_prompt
77
tokens_completion
9081
native_tokens_prompt
76
native_tokens_completion
10151
native_tokens_completion_images
(null)
native_tokens_reasoning
9883
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
0.0792766
router
(null)
provider_responses
0
endpoint_id
"ca7fc0c7-f23d-4ac5-b2e0-945be5b61787"
id
"chatcmpl-83734705-82aa-9df6-8586-ef27db5528f3"
is_byok
false
latency
1260
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-1777286864-NDJ9IhYNL7jPe5nG9V6a"
session_id
(null)
api_type
"completions"
id
"gen-1777286864-GZU9pn3MHIt112xRAP6t"
upstream_id
"chatcmpl-83734705-82aa-9df6-8586-ef27db5528f3"
total_cost
0.0792766
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
100.00%
Dialogue to Total Word Ratio
Ratio: 50.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
100
100.0000%