NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ84BCBNM34GTXS6ZRT1M45
Run Details
Model:
Qwen3 235B A22B Instruct 2507
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
19.7s
Cost:
$0.000195
Provider:
SiliconFlow
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9995%
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
Rain tapped the rooftop of their cramped hatchback as Molly traced crayon-blue lines on a napkin—part floor plan, part fever dream. “Clowns are predictable,” Molly said. “They’re always eating cake or getting pied. We hit during the piñata.” Bill adjusted his sock puppet mask. “What if the kids see us?” “They’ll think we’re part of the act. ‘Look, Mommy, the raccoon’s stealing the Legos!’” “Raccoon? I spent twenty minutes on this!” “You wanted realism. Raccoons steal. It’s scientific.” “I feel typecast.” Molly flicked a chip crumb. “Sentimentality’s a liability. These presents have resale value. That Build-A-Bear could fund three fake mustaches.” “And glitter? Why is there always glitter?” “It’s psychological warfare. You’ll be sneezing through the getaway.” Bill frowned. “What if we get caught by a seven-year-old?” “Then you apologize with authority. ‘I’m sorry, sir, urgent toy redistribution.’ Now—bouncy castle or inflatable slide?” “Bouncy castle. Tactical bounce advantage.” “And the cake?” “Only if it’s chocolate. I have standards.” Molly tapped the napkin. “Distraction at 3:15. You honk the kazoo when the monkey puppet starts dancing.” “What monkey puppet?” “The one you're holding.” Bill looked down. “I’ve had this the whole time?” “Yes. And you’re wearing its pants.”
created_at
"2026-03-25T10:20:04.367Z"
3/25/2026, 10:20:04 AM
model
"qwen/qwen3-235b-a22b-07-25"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1219
moderation_latency
(null)
generation_time
19678
tokens_prompt
77
tokens_completion
401
native_tokens_prompt
72
native_tokens_completion
314
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.00019488
router
(null)
provider_responses
0
endpoint_id
"ce835ea8-00c7-4686-831d-7733dac5e2d9"
id
"019d248230a40a2d01057cc988d48b9a"
is_byok
false
latency
1219
model_permaslug
"qwen/qwen3-235b-a22b-07-25"
provider_name
"SiliconFlow"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1774434004-fjIJmZ9rvQKmM6j0pLsD"
upstream_id
"019d248230a40a2d01057cc988d48b9a"
total_cost
0.00019488
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SiliconFlow"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
199
0.00%
Dialogue to Total Word Ratio
Ratio: 77.94%, Deviation: 27.94%
neededClean
false
wordsTotal
204
wordsDialogue
159
49.9995%