NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ8GY7CE68MZRTPWTKSWKTV
Run Details
Model:
Qwen3 235B A22B Instruct 2507
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
21.9s
Cost:
$0.000202
Provider:
SiliconFlow
Evaluation summary
Score
Evaluator
Details Link
51.93%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
44.3567%
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
“Bill, this is the dumbest plan you’ve ever had. And remember the gold-plated penguin fiasco?” “It’s genius, Molly. Kids’ parties—zero security, maximum distraction. Clowns, chaos, a bouncy castle the size of Cleveland.” “And how do we explain why two grown adults in ski masks are digging through gift-wrapped Barbies?” “We’re undercover. Cousins of the birthday boy. Tragic backstory. Car broke down. Emotional support stealing.” “They’re five, Bill. They don’t care!” “Exactly! They’ll think we’re weird uncles. Which, morally, we kind of are now.” “You brought a duffel bag labeled ‘Presents – Do Not Open’?” “It boosts morale.” “And the getaway? We’re not driving the shopping cart again.” “No, no—this time, I rented a pony.” “A *pony*?” “Small, quiet, blends in. Also comes with a tiny hat.” “You rented a pony… with a hat?” “For ambiance!” “And if the parents ask questions?” “We cry. Loudly. About lost childhood dreams. Works every time.” “This feels wrong.” “It’s not stealing, Molly. It’s redistributing joy. With snacks.” “And the cake?” “Leave the cake. Never fight a child for cake. I learned that in Milwaukee.” “Fine. But if I get attacked by a piñata, I’m blaming you.” “Noted. Now, are you ready to break into the circus of screaming tiny dictators?” “Only if I get the Power Rangers set.” “Deal.”
created_at
"2026-03-25T10:26:56.879Z"
3/25/2026, 10:26:56 AM
model
"qwen/qwen3-235b-a22b-07-25"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3027
moderation_latency
(null)
generation_time
21861
tokens_prompt
77
tokens_completion
420
native_tokens_prompt
72
native_tokens_completion
326
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
0.00020208
router
(null)
provider_responses
0
endpoint_id
"ce835ea8-00c7-4686-831d-7733dac5e2d9"
id
"019d248882c5fe568e29cf1c9bd58395"
is_byok
false
latency
3027
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-1774434416-vAl863njpKPzl0lZ2afg"
upstream_id
"019d248882c5fe568e29cf1c9bd58395"
total_cost
0.00020208
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SiliconFlow"
Evaluation details
Result
Evaluator
Details
Meta Data
51.93%
Matches word count
n/a
neededClean
false
words
216
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
218
wordsDialogue
218
44.3567%