NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ91145KA9EZQ8Q9663RSA2
Run Details
Model:
Qwen 3 32B
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
9.9s
Cost:
$0.000423
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
60.65%
Count dialogue tags
(details)
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 bell above the bakery door chimed as morning sunlight spilled across the flour-dusted countertops. “New to town?” The question came with a warm smile, though the speaker’s eyes lingered on the stranger’s shadow beneath the brim of their hat. “Just passing through,”
the stranger replied
, brushing a crumb from their sleeve. “I’ve heard about this place. The cherry pie’s supposed to be legendary.” “We try our best.” The baker leaned against the counter, arms crossed. “Though you won’t find the same recipe anymore.” “No? Why’s that?” The stranger’s gaze drifted to an old photo of the bakery’s previous owner, tacked behind the register. “She… moved on.” The baker’s chuckle didn’t quite reach her ears. “Left in the middle of the night. Took her cat, her keys, and the secret to that pie.” The stranger tilted their head. “Disappeared? No trace?” “Not a crumb.” A pause. “You could say the town’s still baking in her shadow.” A laugh, low and gravelly. “Small towns always have tales. Some hungrier than others, I bet.” The baker uncapped a jar of jam, rattling the glass. “You could say that. Though I prefer my mysteries served with a dusting of sugar, not suspicion.” “Suspicion’s in the air, isn’t it?” The stranger leaned forward, the scent of black coffee between them. “Heard some folks think she ran. Others think she was pushed.” A flicker of tension. The baker twisted the jar’s lid tighter. “You want a danish, or are you here to stir up old ghosts?” “Neither.” The stranger’s fingers traced the rim of their mug. “Just curious how a place this sweet got so… crusty around the edges.” Outside, a customer called for cinnamon rolls. The baker straightened, apron swishing. “Here’s your coffee. On the house. And if you ask me about the pie again, I’ll have to charge you for the trouble.” The stranger raised their cup. “To secrets that never get stale.” “To that.” The baker turned to the oven, flames licking the dough. “But don’t ask me about the key under the floorboard. That’s just flour.”
created_at
"2026-03-25T10:35:44.139Z"
3/25/2026, 10:35:44 AM
model
"qwen/qwen3-32b-04-28"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
352
moderation_latency
(null)
generation_time
9858
tokens_prompt
98
tokens_completion
1190
native_tokens_prompt
72
native_tokens_completion
998
native_tokens_completion_images
(null)
native_tokens_reasoning
503
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
0.000422656
router
(null)
provider_responses
0
endpoint_id
"344ccdcc-6e59-464d-89ab-8e5b92fe2adc"
id
"chatcmpl-760308f0-a195-90d1-a454-0293584415e6"
is_byok
false
latency
352
model_permaslug
"qwen/qwen3-32b-04-28"
provider_name
"Alibaba"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1774434944-3kVLdRXTlY94lnz12ELp"
upstream_id
"chatcmpl-760308f0-a195-90d1-a454-0293584415e6"
total_cost
0.000422656
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
Evaluation details
Result
Evaluator
Details
Meta Data
60.65%
Count dialogue tags
n/a
neededClean
false
dialogueTags
0
"the stranger replied"