NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK1Q6S758WF3A4CXZPGNVR4
Run Details
Model:
Qwen 3.5 Plus (2026-02-15)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
12.4s
Cost:
$0.000826
Provider:
Alibaba
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 tiny pirate hat, glaring at the colorful mansion. "This is insane, Bill. We are robbing a six-year-old." "It's not insanity, it's strategy," Bill whispered, checking his lockpicks. "Kids get the best loot. High-end tablets, rare Lego sets, cash in envelopes. It's a goldmine wrapped in shiny paper." "They have a clown, Bill. A literal clown guarding the door." "Clowns are predictable. They slip on bananas. It's basic physics." Molly sighed, kicking a stray balloon. "And what about the parents? There are twenty of them drinking punch." "Distraction protocol. You trip the bouncy castle; I grab the hoard. Simple." "I feel like a monster stealing from toddlers." "Think of it as redistribution of wealth. Those kids have too much stuff already." "Fine. But if I get caught by a toddler, I'm blaming you." "Deal. Now, move. The cake cutting is our window." "You realize we might get beaten up by a girl in a tutu." "Unlikely. Their reach is terrible." Molly crept toward the side door, her heart pounding. "Okay, picking the lock now." "Hurry up, I hear singing." "It's open. Let's grab the goods and ghost." "Remember, no taking the giant stuffed unicorn. It's suspicious." "Why? It's huge!" "Exactly. We look ridiculous carrying it." "Fine. Just the tablets." "Go, go, go!"
created_at
"2026-02-16T11:00:24.390867+00:00"
2/16/2026, 11:00:24 AM
model
"qwen/qwen3.5-plus-20260216"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
836
moderation_latency
(null)
generation_time
12369
tokens_prompt
77
tokens_completion
354
native_tokens_prompt
78
native_tokens_completion
331
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
0.0008256
router
(null)
provider_responses
0
id
"chatcmpl-11591698-7cba-9c67-843d-8f999bbe6e6e"
status
200
is_byok
false
latency
836
endpoint_id
"71e0f6c3-7815-4734-92d3-8a04f3b0ca91"
provider_name
"Alibaba"
model_permaslug
"qwen/qwen3.5-plus-20260216"
api_type
"completions"
id
"gen-1771239611-5iPBh4nUk8F6WliPvtBg"
upstream_id
"chatcmpl-11591698-7cba-9c67-843d-8f999bbe6e6e"
total_cost
0.0008256
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
Evaluation details
Result
Evaluator
Details
Meta Data
43.3783%
Matches word count
n/a
neededClean
false
words
217
0.0000%
Dialogue to Total Word Ratio
Ratio: 85.71%, Deviation: 35.71%
neededClean
false
wordsTotal
217
wordsDialogue
186
21.6892%