NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5GSG8WQHWE8P2F6C394ZR
Run Details
Model:
DeepSeek V3.2
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
8.5s
Cost:
$0.000121
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 sharp, cheerful sound in the quiet room. “You’re here early. The cinnamon rolls are still sleeping.” “I need your help, and I needed to get out before anyone saw me. It’s about the garden show trophy.” “The one that went missing from the library display? The sugar cookies can wait. Start talking.” “I saw something last night. A shadow, moving behind the hydrangeas at the old Miller place. It was carrying something long and wrapped in cloth.” “The Miller place? But that’s been abandoned for years. Are you sure it wasn’t just a trick of the moonlight?” “Positive. And this morning, I found this caught on my own rose bush.” A small, metallic click as an object was placed on the glass counter. “A silver wishing-coin from the festival? Half the town has one of these.” “Not like this. Look at the ribbon. It’s lavender satin, hand-dyed. There’s only one person in this county who uses that particular shade.” “Oh. Oh, my. Well. Let me just box up a couple of those bear claws. I think we should pay a visit to the hydrangeas.”
created_at
"2026-02-16T21:25:59.165533+00:00"
2/16/2026, 9:25:59 PM
model
"deepseek/deepseek-v3.2-20251201"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1031
moderation_latency
(null)
generation_time
8431
tokens_prompt
81
tokens_completion
300
native_tokens_prompt
65
native_tokens_completion
258
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
0.000120685
router
(null)
provider_responses
0
id
"0d83f8c2f0c0ec48152f880fb6943e87"
status
200
is_byok
false
latency
1031
endpoint_id
"8a5fb6d3-ef71-4958-af54-269ffa3a3c6e"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-v3.2-20251201"
api_type
"completions"
id
"gen-1771277149-5KY2gpkUKvb3DLNtibjt"
upstream_id
"0d83f8c2f0c0ec48152f880fb6943e87"
total_cost
0.000120685
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)