NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5D9G5PFGRB1YMX6737FT4
Run Details
Model:
DeepSeek V3 (2024-12-26)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
11.4s
Cost:
$0.000410
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 warm bread wrapped around the newcomer like a hug. "Morning! You’re here early." "Couldn’t sleep. Thought I’d get a head start on the day. Those scones smell divine." "Fresh out of the oven. Blueberry or lemon today?" "Surprise me. You know I trust your judgment." A plate clinked against the counter, followed by the soft scrape of a knife. "Here. Lemon with a hint of lavender. New recipe." "Mmm. Perfect. You’re a genius." "Flattery won’t get you a discount." "Worth a try. Say, have you heard about the missing garden gnome from Mrs. Peabody’s yard?" "The one with the little fishing rod? Who’d take that?" "Beats me. But she’s convinced it’s foul play. Swears she saw footprints leading toward the woods." "Or maybe it’s just Old Man Higgins playing pranks again." "Maybe. But if gnomes are going missing, what’s next? The town’s in chaos." "Chaos? Over a gnome?" "Stranger things have happened in this town." "True. Pass the sugar, will you? I need something sweet to balance out this mystery."
created_at
"2026-02-16T21:24:07.166927+00:00"
2/16/2026, 9:24:07 PM
model
"deepseek/deepseek-chat-v3"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1313
moderation_latency
(null)
generation_time
11370
tokens_prompt
81
tokens_completion
311
native_tokens_prompt
64
native_tokens_completion
296
native_tokens_completion_images
0
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
0.0004104
router
(null)
provider_responses
0
id
"0463c9201473039003ad1e6db0716ea2"
status
200
is_byok
false
latency
1313
endpoint_id
"cefb5a1e-9fea-4496-9a64-4e1b11a7cc8c"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-chat-v3"
api_type
"completions"
id
"gen-1771277035-cYTNCRpIREE4VX2twyCt"
upstream_id
"0463c9201473039003ad1e6db0716ea2"
total_cost
0.0004104
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)