NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ74G49C5ZWGY5VHTRED2R3M
Run Details
Model:
Qwen 3.6 35B
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
17.5s
Cost:
$0.002416
Provider:
AtlasCloud
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 sharply, cutting through the heavy scent of yeast and caramelized sugar. Dust motes danced in the shafts of morning light that pierced the glass display case, illuminating rows of perfect pastries. "You're late, Martha. The scones won't rise by themselves, and the oven's been screaming at me for ten minutes." "I know, I know. The police cruiser is parked right outside, blocking the old maple tree. I had to double back past the post office." "The police? Here? At the bakery? This close to the town bake-off?" "They found something in the crumb tray, Elsie. Or maybe in the blueberry muffin tin. It wasn't a criminal, though." "Oh, dear. Did the Mayor get sick again?" "Worse. They found a ledger tucked under the flour sack. A real ledger, signed in red ink. The kind Mayor Henderson uses for his 'off-book' donations." "A ledger? But that's the Mayor's secret gambling den!" "Exactly. And I think the baker knows exactly where it came from. He's been sweating through his apron." "Then lock the back door, dear. And hand me that rolling pin. If Detective Miller walks in, we'll need something heavier than a whisk to defend our reputation."
created_at
"2026-04-27T09:32:02.739Z"
4/27/2026, 9:32:02 AM
model
"qwen/qwen3.6-35b-a3b-20260415"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
673
moderation_latency
(null)
generation_time
17439
tokens_prompt
81
tokens_completion
2712
native_tokens_prompt
78
native_tokens_completion
2490
native_tokens_completion_images
(null)
native_tokens_reasoning
2206
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
0.002416046
router
(null)
provider_responses
0
endpoint_id
"179c6985-3a1c-48f1-a009-9f3e3e402cdd"
id
"30de41e07c944042aac273d5432d2f5b"
is_byok
false
latency
673
model_permaslug
"qwen/qwen3.6-35b-a3b-20260415"
provider_name
"AtlasCloud"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777282322-IkHjlmJ4uEKyMS1HB6oj"
session_id
(null)
api_type
"completions"
id
"gen-1777282322-JJGFaZOJprHrLBS8cppD"
upstream_id
"30de41e07c944042aac273d5432d2f5b"
total_cost
0.002416046
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AtlasCloud"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)