NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2HDDYWJV4V965J59GCH7HV
Run Details
Model:
DeepSeek V4 Pro (Reasoning)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
14.5s
Cost:
$0.000412
Provider:
DeepSeek
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 scent of fresh cinnamon rolls curled through the air, cozy and warm, a stark contrast to the chill that had settled over the knitting circle’s usual corner table. “You’d think the mayor would have better sense than to accuse Francine of tampering with his bear claw. In her own bakery, for heaven’s sake.” “The man’s stomach turned sour, that’s all. He’s been eating his feelings since the election. Besides, everyone knows Francine only adds almonds, never arsenic.” A soft clink of a coffee cup meeting its saucer punctuated the pause. Through the display case glass, a row of glazed donuts stared blankly out at the empty sidewalk. “Nostalgia is a funny thing, isn’t it? He swore it tasted exactly like the one he had the day before his first heart attack. A warning, he called it.” “The only warning I see is a three-time chili cook-off champion who forgot he developed a nut allergy last spring. His wife told the book club. He carries an epi-pen now, tucked inside that ridiculous ten-gallon hat.” “Perhaps. But why would Francine bolt the back door and leave her reading glasses on the counter, right next to a spatula coated in almond paste?”
created_at
"2026-04-25T14:41:33.664Z"
4/25/2026, 2:41:33 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1232
moderation_latency
(null)
generation_time
14501
tokens_prompt
81
tokens_completion
515
native_tokens_prompt
65
native_tokens_completion
441
native_tokens_completion_images
(null)
native_tokens_reasoning
173
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
0.000411945
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"136d3fb5-2189-40e3-9165-3c5220344cf2"
is_byok
false
latency
335
model_permaslug
"deepseek/deepseek-v4-pro-20260423"
provider_name
"DeepSeek"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777128093-rKUHnmNs8KmiqGAJuXBi"
session_id
(null)
api_type
"completions"
id
"gen-1777128093-tvhXCnK7oBIQxtBzXvUE"
upstream_id
"136d3fb5-2189-40e3-9165-3c5220344cf2"
total_cost
0.000411945
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)