NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK12NYMPXHZ0BMNF1TEBFBS
Run Details
Model:
Qwen 3.5 Plus (2026-02-15)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
13.0s
Cost:
$0.000871
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 shaking. We are stealing from toddlers, not a bank vault." "Molly, have you seen the security? It's a clown. A giant, honking clown." "The clown is distracted by a balloon animal crisis. We slip in during 'Happy Birthday.'" "And the mom? The one with the whistle?" "She'll be blowing out candles. That's our window. Thirty seconds max." "Thirty seconds to grab fifty wrapped boxes? Do the math, Mol." "We don't take all fifty. We take the big ones. The ones that rattle like electronics." "What if they're just noisy toys? What if we get caught holding a squeaky hammer?" "Then we run. You're faster than me anyway." "I am not faster than you when I'm carrying a stack of Lego sets!" "Think of the resale value, Bill. Pure profit. No alarms, just juice boxes." "Juice boxes stain, Molly. I'm wearing my good suit." "Wear the jumpsuit. Blend in as entertainment. You look like a sad mime already." "Says the woman dressed as a fairy godmother with a black eye." "That's part of the character. Now, when the cake comes out, we move." "I still think the clown suspects us." "The clown is high on sugar fumes. Trust me. On three. One, two..." "Wait, did that four-year-old just spot us?" "Smile and wave. Act like you're here to fix the piƱata." "This is the worst idea we've ever had." "Exactly. That's why it'll work. Go!"
created_at
"2026-02-16T10:49:12.12266+00:00"
2/16/2026, 10:49:12 AM
model
"qwen/qwen3.5-plus-20260216"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
759
moderation_latency
(null)
generation_time
12635
tokens_prompt
77
tokens_completion
349
native_tokens_prompt
78
native_tokens_completion
350
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
0.0008712
router
(null)
provider_responses
0
id
"chatcmpl-2a8bf11d-ad0a-9c40-bb78-fc37e8c8b6b2"
status
200
is_byok
false
latency
759
endpoint_id
"71e0f6c3-7815-4734-92d3-8a04f3b0ca91"
provider_name
"Alibaba"
model_permaslug
"qwen/qwen3.5-plus-20260216"
api_type
"completions"
id
"gen-1771238938-MdHyTMMAfWzkCeDSYqit"
upstream_id
"chatcmpl-2a8bf11d-ad0a-9c40-bb78-fc37e8c8b6b2"
total_cost
0.0008712
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
238
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
238
wordsDialogue
238
18.3940%