NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5BVPT52JSJA8483MYGAQG
Run Details
Model:
DeepSeek V3.1
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
7.6s
Cost:
$0.000248
Provider:
AtlasCloud
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 chimed, a cheerful sound at odds with the grim morning. “You’ve heard, then?” “The whole town’s heard. It’s all anyone can talk about. A shame, a real shame.” “And right next door, too. Makes the cinnamon rolls taste like ash, if you ask me. Did you see anything? Anything at all?” “Just the police cars, their lights flashing against the frosting on the wedding cakes. A dreadful contrast. He always ordered a lemon tart on Fridays. Always.” “Such a creature of habit. It feels wrong, baking scones as if the world hasn’t tilted on its axis.” “The world tilts, dear, but the oven timer waits for no one. We have our orders to fill. Besides, the constable will be in for his usual soon. He’ll want a strong coffee and a quiet corner.” “Do you think he’ll tell us anything?” “He won’t have to. I’ll just watch which way he looks when he walks past Mrs. Hawthorne’s blackberry jam thumbprints. That will tell me everything I need to know.”
created_at
"2026-02-16T21:23:16.730716+00:00"
2/16/2026, 9:23:16 PM
model
"deepseek/deepseek-chat-v3.1"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
899
moderation_latency
(null)
generation_time
7534
tokens_prompt
100
tokens_completion
272
native_tokens_prompt
66
native_tokens_completion
240
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.0002478
router
(null)
provider_responses
0
id
"49656354b03848e4a1909cc9bba67f79"
status
200
is_byok
false
latency
899
endpoint_id
"0bfe3535-ed02-47ea-a98f-60cc8af4fab2"
provider_name
"AtlasCloud"
model_permaslug
"deepseek/deepseek-chat-v3.1"
api_type
"completions"
id
"gen-1771276988-tW8rgymEQCtg0QRnSiGV"
upstream_id
"49656354b03848e4a1909cc9bba67f79"
total_cost
0.0002478
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AtlasCloud"
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)