NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ70J8ZSH1ZSKKF64XGTY4DY
Run Details
Model:
Qwen 3.5 Plus (2026-04-20)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
57.7s
Cost:
$0.009151
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
Flour dust hovered in the warm air, coating the oak counter. A ceramic plate slid past a basket of sticky buns. "Best batch yet. Grandma's yeast is the secret. It wakes up the flour like magic." A rough hand rubbed a neck; eyes darted toward the damp window. "I'm not here for bread, Edith. I saw a state car two blocks down. The driver was asking about the storm drains near the creek. Very specific questions." The wooden paddle tapped a nervous rhythm. "State cars pass through every election, harping on drainage permits. Tell them to return when the scones are set. I won't have a draft kill my rise while they waste my time." "This isn't politics. The badge looked too shiny, and he flashed a photo of a locket." The voice dropped. "Does that sound routine? The locket belonged to Martha." Edith didn't look up, though her grip tightened on the paddle. "Wrap the loaf in brown paper. Double wrap. And if anyone asks, you weren't here. Not while that sedan is prowling." The bell above the door jingled faintly in the wind, making both speakers freeze. Edith slid a small tin across the counter, hidden beneath the newspaper. "Take the almond cookies. If they search, let them find crumbs, not secrets."
created_at
"2026-04-27T08:23:18.786Z"
4/27/2026, 8:23:18 AM
model
"qwen/qwen3.5-plus-20260420"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
701
moderation_latency
(null)
generation_time
57609
tokens_prompt
81
tokens_completion
3870
native_tokens_prompt
78
native_tokens_completion
3800
native_tokens_completion_images
(null)
native_tokens_reasoning
3511
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
0.0091512
router
(null)
provider_responses
0
endpoint_id
"8b4a0fbb-6705-4f8d-a7f1-ad18ecc0edbc"
id
"chatcmpl-2d7112bb-3617-9b53-8d73-1d7d48be62e0"
is_byok
false
latency
669
model_permaslug
"qwen/qwen3.5-plus-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-1777278198-0KC9px3fOuAQQPveGioj"
session_id
(null)
api_type
"completions"
id
"gen-1777278198-PW2bXCqGNGLY8gnSlRty"
upstream_id
"chatcmpl-2d7112bb-3617-9b53-8d73-1d7d48be62e0"
total_cost
0.0091512
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)