NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ831836MXS3V2AR2MJRY2N
Run Details
Model:
Qwen3 235B A22B Instruct 2507
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
23.6s
Cost:
$0.000219
Provider:
SiliconFlow
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0014%
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 adjusted her black beanie, squinting through the window of Chuckles the Clown’s Birthday Barn. "You really think parents leave five hundred bucks’ worth of gifts unattended?" Bill gnawed on a licorice whip. "It’s a clown museum, Molly. Security’s a guy named Gary who naps during magic shows." "So we’re stealing toys from toddlers?" "Precisely. And cash. Always follow the cash." "Bill, there’s a piñata shaped like a duck the size of a small pony. Someone stuffed it with something valuable." "Or raisins. It’s a kids’ party, Molly. Not Fort Knox." "Neither was the yarn store, and we got that gold knitting needle." "That was a one-time fluke. Now focus. Distraction plan?" "You go in as a late guest. I’m the angry ex-wife crashing the party." "Ex-wife? Since when are we married?" "Improvisation, Bill. It’s called improvisation." "Fine. But if you start crying about my golf clubs again, I’m bailing." "Relax. I’ll even bring tissues. The glitter kind." "Why glitter?" "Because when security reviews footage, they’ll be too busy sneezing to notice the duffel full of talking unicorns." "Talking unicorns? Those things are cursed." "Only if you ignore their feelings. Wait… is that Gary? He’s wearing footie pajamas." "Told you. Security's a joke." "Then this heist is a sure thing. Just don’t eat the cotton candy. Last time you did, you cried through *Finding Nemo*." "Hey, that whale had a rough life!"
created_at
"2026-03-25T10:19:21.224Z"
3/25/2026, 10:19:21 AM
model
"qwen/qwen3-235b-a22b-07-25"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1929
moderation_latency
(null)
generation_time
23557
tokens_prompt
77
tokens_completion
400
native_tokens_prompt
72
native_tokens_completion
355
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
0.00021948
router
(null)
provider_responses
0
endpoint_id
"ce835ea8-00c7-4686-831d-7733dac5e2d9"
id
"019d2481892c6dc05c3e4ce81231203c"
is_byok
false
latency
1929
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-1774433961-8WrOjrfA1Hco8iFYYMSi"
upstream_id
"019d2481892c6dc05c3e4ce81231203c"
total_cost
0.00021948
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SiliconFlow"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
232
0.00%
Dialogue to Total Word Ratio
Ratio: 91.03%, Deviation: 41.03%
neededClean
false
wordsTotal
234
wordsDialogue
213
0.0014%