NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK3A4Z58375SVRFJ3QA7ZQY
Run Details
Model:
Qwen 3.5 Plus (2026-02-15)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
14.8s
Cost:
$0.000800
Provider:
Alibaba
Model input
User/Human
You are an expert novel writer in the cozy mystery genre. Write a scene of about 200 words, with dialogue between two characters. The dialogue should be unattributed, meaning the speaker is not explicitly mentioned. The scene should be set in a small town bakery. Only return the story, nothing else.
Model response
Messages
Meta
AI
"The cinnamon rolls look a bit darker than usual today,"
the customer noted, tapping a manicured nail against the glass display case
. "Just a new oven setting. Gives them a nice caramelized crunch,"
the baker replied, not looking up from the flour-dusted counter
. "Same as always, Mrs. Gable? One coffee, black, and a scone?" "Actually, I think I'll try one of those rolls. And maybe you can tell me why the police car has been parked outside your back door since six this morning?" The baker's hand paused mid-reach for a tongs. "Delivery mix-up. They needed directions to the old mill." "At six in the morning on a Sunday? That mill hasn't operated in twenty years. And since when do deliveries require two officers and a yellow tape perimeter?" "It's a quiet town, Mrs. Gable. Sometimes quiet gets loud for no reason." "Quiet towns don't have body bags, dear. My husband saw them wheeling something out covered in a sheet. Looked about the size of young Tommy Miller." "Tommy's fine. He was just here an hour ago buying donuts." "Was he? Because the sheet seemed to have very distinct red stains on the corner. The kind that don't wash out of aprons, either." The baker finally met her gaze, eyes narrowing slightly. "You're imagining things. Here's your roll. That'll be four dollars." "Keep the change. You'll need it for a good lawyer."
created_at
"2026-02-16T11:28:15.810393+00:00"
2/16/2026, 11:28:15 AM
model
"qwen/qwen3.5-plus-20260216"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
764
moderation_latency
(null)
generation_time
14763
tokens_prompt
81
tokens_completion
353
native_tokens_prompt
80
native_tokens_completion
320
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
0.0008
router
(null)
provider_responses
0
id
"chatcmpl-207aaf76-ff5b-9165-ae14-fbb5f98d405e"
status
200
is_byok
false
latency
764
endpoint_id
"71e0f6c3-7815-4734-92d3-8a04f3b0ca91"
provider_name
"Alibaba"
model_permaslug
"qwen/qwen3.5-plus-20260216"
api_type
"completions"
id
"gen-1771241280-uBwG2bGXYsYkX4GbWJTg"
upstream_id
"chatcmpl-207aaf76-ff5b-9165-ae14-fbb5f98d405e"
total_cost
0.0008
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
Evaluation details
Result
Evaluator
Details
Meta Data
13.5335%
Count dialogue tags
n/a
neededClean
false
dialogueTags
0
"the customer noted, tapping a manicured nail against the glass display case"
1
"the baker replied, not looking up from the flour-dusted counter"