NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5ZNND19XFCGK76D63TMDK
Run Details
Model:
DeepSeek V3.1
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
17.0s
Cost:
$0.000246
Provider:
Novita
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 merry little sound at odds with the grim discussion. “I just don’t see how it could have been an accident. Arthur was terrified of bees, you know.” “He was covered in flour, for goodness’ sake. It was his own clumsiness.” “Clumsy enough to trip and fall face-first into a vat of sourdough starter? The lid was still on it. And where did the bee come from? It’s February.” “A very persistent bee. You sprinkle a little powdered sugar on a man with a bee allergy, and suddenly it’s foul play.” “It wasn’t just sugar. You’d have to get close to do that. Very close. Did you know he’d ended things with Beatrice? Just last week.” “The Beatrice who makes our croissants? The one whose special blend of honey was found on his collar?” The warm, yeasty air of the bakery suddenly felt cold. Outside, a car rolled slowly past the window, its driver’s face obscured by the glare of the morning sun.
created_at
"2026-02-16T21:34:14.96855+00:00"
2/16/2026, 9:34:14 PM
model
"deepseek/deepseek-chat-v3.1"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
828
moderation_latency
(null)
generation_time
6776
tokens_prompt
100
tokens_completion
258
native_tokens_prompt
66
native_tokens_completion
228
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
0.00024582
router
(null)
provider_responses
0
status
(null)
is_byok
false
latency
10100
endpoint_id
"5d5c9c1d-af0d-4e4a-8aee-c5cd2b3883f3"
provider_name
"SiliconFlow"
model_permaslug
"deepseek/deepseek-chat-v3.1"
1
id
"607867b2-f724-4de8-8b8a-35e3b3b9ba81"
status
200
is_byok
false
latency
828
endpoint_id
"715d05e1-9fa7-4ceb-834a-833f5e26a55a"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-chat-v3.1"
api_type
"completions"
id
"gen-1771277637-xqsSgv3P0i2lYuE7RWmg"
upstream_id
"607867b2-f724-4de8-8b8a-35e3b3b9ba81"
total_cost
0.00024582
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)