NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ77NFQFE67XDDQZ8JC4X84T
Run Details
Model:
Qwen3.6 Max Preview
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
1m 24s
Cost:
$0.019383
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 jingled, cutting through the scent of rising yeast and caramelized sugar. Dust motes danced in the morning light streaming past the display case of glazed crullers. The oven timer buzzed, sharp and demanding. "You heard about the Mayor?" "Hard not to. The whole town's whispering over their morning croissants." "They found him slumped over the ledger in the town hall. Face blue as a blackberry tart." "Blue? That's not natural. Did he eat anything before he went in? He always stops for his espresso first." "Just the special delivery from here. The almond brioche you wrapped in pink paper. No espresso cup in sight." "I wrapped three pink brioches this morning. One for the librarian, one for the florist, and one for the Mayor. The librarian and florist are fine. I saw Mrs. Gable eating hers on the bench." "Maybe. Or maybe someone switched the bags after they left the counter. The back door was unlatched when I arrived." "The security camera's been broken since the fall festival." "Convenient. Hand me that rolling pin, will you? If the Sheriff comes asking, we need these scones to look perfectly innocent. And wipe the flour off your apron; you're shaking."
created_at
"2026-04-27T10:27:24.024Z"
4/27/2026, 10:27:24 AM
model
"qwen/qwen3.6-max-preview-20260420"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1193
moderation_latency
(null)
generation_time
83589
tokens_prompt
81
tokens_completion
2659
native_tokens_prompt
78
native_tokens_completion
2472
native_tokens_completion_images
(null)
native_tokens_reasoning
2190
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
0.019383
router
(null)
provider_responses
0
endpoint_id
"ca7fc0c7-f23d-4ac5-b2e0-945be5b61787"
id
"chatcmpl-29774b5c-eefb-91e1-a6ce-517d5227bd0b"
is_byok
false
latency
1193
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-1777285644-LStqL7OGQYZrKNDY5aFI"
session_id
(null)
api_type
"completions"
id
"gen-1777285644-uONviLTsHmzEEXjZPM42"
upstream_id
"chatcmpl-29774b5c-eefb-91e1-a6ce-517d5227bd0b"
total_cost
0.019383
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)