NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK3648S299KY7EPSYKJKXJM
Run Details
Model:
Qwen 3.5 Plus (2026-02-15)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
12.6s
Cost:
$0.000802
Provider:
Alibaba
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, stop eating the map. We need to hit the birthday bash at six." "Why a kids' party, Molly? The security is tight. Those clowns are trained assassins." "Exactly. Nobody suspects the clown. Plus, the loot is pure gold. LEGO sets, video games, cash envelopes." "Cash in envelopes? Since when do eight-year-olds carry non-biodegradable currency?" "Rich kids, Bill. Think of the payout. We grab the pile by the castle bounce-house and vanish." "And the getaway vehicle? A minivan with 'Just Married' signs?" "No, we use the pony ride. It's unexpected. Now, what's the code for the back door?" "I heard the mom scream it to the dad. It's 'Sparkle123'." "Sparkle? Really? That's the password? This job is getting sadder by the minute." "Focus, Bill. We wear the mascot costumes. The giant dinosaur and the purple dragon." "I am not wearing the purple dragon suit again. It chafes in places that shouldn't chafe." "Do you want the Nintendo Switch or not? Because I can do this with Steve." "Fine! But if I get glitter in my eyes, I'm quitting the gang." "Deal. Now hide the crowbar behind the piƱata. Here comes the cake." "Is that a sword inside the cake?" "No, Bill, that's just a very aggressive candle. Move it, dragon-boy."
created_at
"2026-02-16T11:26:01.487274+00:00"
2/16/2026, 11:26:01 AM
model
"qwen/qwen3.5-plus-20260216"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
899
moderation_latency
(null)
generation_time
12511
tokens_prompt
77
tokens_completion
319
native_tokens_prompt
78
native_tokens_completion
321
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
0.0008016
router
(null)
provider_responses
0
id
"chatcmpl-a31eb026-223a-9e3c-8570-93f8058da38d"
status
200
is_byok
false
latency
898
endpoint_id
"71e0f6c3-7815-4734-92d3-8a04f3b0ca91"
provider_name
"Alibaba"
model_permaslug
"qwen/qwen3.5-plus-20260216"
api_type
"completions"
id
"gen-1771241148-erOZGLGo1j6ZT17pmpwz"
upstream_id
"chatcmpl-a31eb026-223a-9e3c-8570-93f8058da38d"
total_cost
0.0008016
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
Evaluation details
Result
Evaluator
Details
Meta Data
60.2752%
Matches word count
n/a
neededClean
false
words
215
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
215
wordsDialogue
215
48.5316%