NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5KMYRBPRZ3CWZ7GQP2DVT
Run Details
Model:
DeepSeek V3 (2024-12-26)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
8.7s
Cost:
$0.000395
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 bakery door jingled, and the scent of cinnamon and butter wrapped around the newcomer like a warm hug. "Is that you? I’d recognize that impatient stomp anywhere." "Impatient? I’ve been standing outside for five minutes debating whether to come in at all." "Debating? Over my famous apple turnovers? That’s a first." "Maybe I’m watching my waistline." "Since when? You ate three of my scones last Tuesday." "Fine. You caught me. I’m avoiding Margaret. She’s been lurking near the post office, and you know how she gets when she’s on one of her ‘community improvement’ kicks." "Oh, don’t worry. She already stopped by this morning—something about ‘excessive sugar’ and ‘corrupting the youth.’" "Tell me you didn’t give her a free muffin to go away." "Of course I did. Blueberry. Her favorite." "You’re enabling her." "And you’re avoiding the real issue. You didn’t come here to hide from Margaret. You came for the turnovers." "...Maybe." "Thought so. They’re in the back. Fresh out of the oven." "Lead the way. But if Margaret asks, I was never here."
created_at
"2026-02-16T21:27:32.753576+00:00"
2/16/2026, 9:27:32 PM
model
"deepseek/deepseek-chat-v3"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
914
moderation_latency
(null)
generation_time
8640
tokens_prompt
81
tokens_completion
314
native_tokens_prompt
64
native_tokens_completion
284
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
0.0003948
router
(null)
provider_responses
0
id
"13411ed7cf9daf1fd923a0f36ca2e173"
status
200
is_byok
false
latency
914
endpoint_id
"cefb5a1e-9fea-4496-9a64-4e1b11a7cc8c"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-chat-v3"
api_type
"completions"
id
"gen-1771277243-7TBMFXgu4Mf5wTsY8h7G"
upstream_id
"13411ed7cf9daf1fd923a0f36ca2e173"
total_cost
0.0003948
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)