NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ782MXCKDYJXYECAZHYDRJZ
Run Details
Model:
Qwen3.6 Max Preview
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
1m 47s
Cost:
$0.029000
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
100.00%
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 door chimed, scattering flour dust from the rafters. Sunlight caught the glass display case, warming the rows of raspberry tarts and braided challah. The air hung thick with cardamom and browned butter. “You left the back window unlatched again.” “I needed the steam to escape. The ovens have been running since three.” “Steam doesn’t leave muddy boot prints on the pantry tiles.” A wooden spoon clattered against the copper mixing bowl. The checkerboard floor creaked under shifting weight. “Did you touch the envelope?” “The one tucked beneath the sugar canister? I wouldn’t dare. It’s still sealed, though the wax looks exactly like the mayor’s crest.” “He hasn’t used that seal since the library fire.” “Exactly. Which means someone’s recycling old stationery, or we’re about to host very unwanted company.” “The sourdough starter’s bubbling over. Hand me the linen towel.” “Only if you promise to call Sheriff Higgins before the next batch goes in.” “I’ll call him. But first, taste this crumb. Tell me if it’s almond extract or something far more bitter.” “You’re baking clues again, aren’t you?” “Only until the truth rises.”
created_at
"2026-04-27T10:34:35.317Z"
4/27/2026, 10:34:35 AM
model
"qwen/qwen3.6-max-preview-20260420"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1270
moderation_latency
(null)
generation_time
106989
tokens_prompt
81
tokens_completion
3424
native_tokens_prompt
78
native_tokens_completion
3705
native_tokens_completion_images
(null)
native_tokens_reasoning
3432
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.0290004
router
(null)
provider_responses
0
endpoint_id
"ca7fc0c7-f23d-4ac5-b2e0-945be5b61787"
id
"chatcmpl-3bb6fa87-64af-9626-84bd-a5c55d654123"
is_byok
false
latency
1270
model_permaslug
"qwen/qwen3.6-max-preview-20260420"
provider_name
"Alibaba"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777286075-16TPxpfHKXztPGdsbgfs"
session_id
(null)
api_type
"completions"
id
"gen-1777286075-7vX9k3ePaA235nSEmMCS"
upstream_id
"chatcmpl-3bb6fa87-64af-9626-84bd-a5c55d654123"
total_cost
0.0290004
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)