NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ9233DRTMBBK1FQTBCBR31
Run Details
Model:
Qwen3 235B A22B Instruct 2507
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
22.5s
Cost:
$0.000215
Provider:
SiliconFlow
Evaluation summary
Score
Evaluator
Details Link
60.28%
Matches word count
(details)
99.13%
Dialogue to Total Word Ratio
(details)
79.7036%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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 crouched behind a bush, binoculars pressed to her face. “You said this was a jewelry warehouse.” Bill adjusted his ski mask. “It was! Then they moved. Birthday party’s renting the space.” “Bill, that’s seven clowns and a bounce house.” “And thirty unattended gift bags. You see that piñata? Stuffed like a mob boss’s mattress.” “Those are for kids.” “So were my dreams, Molly. Doesn’t mean I crushed them with a shovel.” “You can’t steal from children.” “I can and I will. They don’t even appreciate the toys. They break 'em in ten minutes. We’ll liberate them. Humanitarian mission.” “You’re wearing sparkly dinosaur pajamas.” “Stealth. Kids trust dinosaurs. Also, I forgot my black outfit.” “How do you forget your black outfit?” “It was in the wash! With the glitter socks. Now everything looks like a disco crime scene.” “Fine. But if we get caught by a toddler, I’m blaming you.” “Agreed. Now, do we hit the wrapped ones first or go straight for the candy-filled piñata?” “Piñata. Cops never check the candy.” “Smart. I brought the bat.” “Is it clean?” “It’s pink and says ‘Happy Birthday, Timmy.’” “Perfect. Let’s make Timmy cry.” “Molly, you’re a monster.” “They said the same about Napoleon.” “And look how he ended up.” “Exactly. In exile. With no presents.” “Touché.”
created_at
"2026-03-25T10:36:18.929Z"
3/25/2026, 10:36:18 AM
model
"qwen/qwen3-235b-a22b-07-25"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1453
moderation_latency
(null)
generation_time
22472
tokens_prompt
77
tokens_completion
422
native_tokens_prompt
72
native_tokens_completion
347
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
0.00021468
router
(null)
provider_responses
0
endpoint_id
"ce835ea8-00c7-4686-831d-7733dac5e2d9"
id
"019d24910ff6d0acd9e56b104700f451"
is_byok
false
latency
1453
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-1774434978-Xpk9OkBefdl6jt7oTzXX"
upstream_id
"019d24910ff6d0acd9e56b104700f451"
total_cost
0.00021468
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SiliconFlow"
Evaluation details
Result
Evaluator
Details
Meta Data
60.28%
Matches word count
n/a
neededClean
false
words
215
99.13%
Dialogue to Total Word Ratio
Ratio: 93.06%, Deviation: 3.06%
neededClean
false
wordsTotal
216
wordsDialogue
201
79.7036%