NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KAST04YC4YZMX316QKCAR2
Run Details
Model:
DeepSeek V4 Flash 0731 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
6.2s
Cost:
$0.000157
Provider:
Baidu
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 cinnamon rolls were cooling on the counter, their glaze still shimmering. The morning light caught the dust in the air like a secret. “You’re in early.” “So are you. And you’re using the good vanilla.” “I always use the good vanilla. You’re the one who’s been skimping on the almond extract.” A pause, filled by the clatter of a whisk against a copper bowl. The older woman wiped her hands on her apron, leaving a smear of flour across her hip. “That batch you sold to the mayor’s wife,”
she said
, not looking up. “She found something in it. Something… not supposed to be there.” The younger woman laughed—a light, tinkling sound that didn’t reach her eyes. “A hair? A burnt raisin? She’s always been dramatic.” “It wasn’t a raisin. It was a button. A pearl button. From a cardigan. The one your aunt wore, the day she went missing.” The whisk stopped. The air turned thick as honey. “I don’t know what you’re talking about.” “Don’t you? She had that button in her pocket when she came in here that morning. I remember because she was fiddling with it, nervous. And then she left—and you told everyone she’d caught the bus to the city.” The younger woman turned slowly, her face pale as the flour dust. “Why are you telling me this now?” “Because I just found the other one. Under the mixer.”
created_at
"2026-09-03T09:50:02.774Z"
9/3/2026, 9:50:02 AM
model
"deepseek/deepseek-v4-flash-20260731"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1136
moderation_latency
(null)
generation_time
6148
tokens_prompt
78
tokens_completion
544
native_tokens_prompt
144
native_tokens_completion
488
native_tokens_completion_images
(null)
native_tokens_reasoning
160
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"
service_tier
(null)
usage
0.0001568
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788429002-z5hAlmWMgKr2meExO01F"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788429002-yAIWQY9HWcJCSMNiDOMI"
upstream_id
"as-dkvqfbzbzn"
provider_responses
0
endpoint_id
"223c54e7-4db1-4098-980f-47741e7637ab"
id
"as-dkvqfbzbzn"
is_byok
false
latency
1136
model_permaslug
"deepseek/deepseek-v4-flash-20260731"
provider_name
"Baidu"
status
200
total_cost
0.0001568
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Baidu"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
60.65%
Count dialogue tags
n/a
neededClean
false
dialogueTags
0
"she said"