NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5SEMS5PNV95X8MQPWSVXZ
Run Details
Model:
DeepSeek V3.1
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
8.3s
Cost:
$0.000303
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 little bell above the door of The Rising Roll jingled, announcing the first customer of the morning. “It smells like heaven in here. Is that the cinnamon apple danish?” “Fresh from the oven. I added a touch of cardamom this time. Let me get you a sample.” “Oh, my. That’s divine. You’re going to put the city bakeries out of business, not that I’m complaining.” “Flattery will get you an extra dollop of icing. The usual, plus one of these?” “Make it two. I need the extra fortification. You’ll never guess what I just saw.” “Try me. The grapevine has been suspiciously quiet this week.” “Eliza Middleton, marching into the mayor’s office at seven-thirty in the morning, waving a zoning pamphlet like a battle flag.” “No! Not about the proposed expansion of the dog park?” “The very same. She was purple, absolutely purple. Said the barking would disturb the historical serenity of the neighborhood.” “Historical serenity? Her poodle, Pierre, is the only one who barks. And only at squirrels. This is about that petty squabble over her rose bushes last summer.” “Precisely. I’d say there’s a mystery afoot, and it’s not nearly as sweet as your pastries.”
created_at
"2026-02-16T21:30:42.162126+00:00"
2/16/2026, 9:30:42 PM
model
"deepseek/deepseek-chat-v3.1"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
861
moderation_latency
(null)
generation_time
8148
tokens_prompt
100
tokens_completion
332
native_tokens_prompt
66
native_tokens_completion
285
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
0.00030282
router
(null)
provider_responses
0
id
"e1977209-3683-430a-bd63-5b9fe6aff63b"
status
200
is_byok
false
latency
861
endpoint_id
"715d05e1-9fa7-4ceb-834a-833f5e26a55a"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-chat-v3.1"
api_type
"completions"
id
"gen-1771277433-8Pviz5espg2Z6CDEiXyp"
upstream_id
"e1977209-3683-430a-bd63-5b9fe6aff63b"
total_cost
0.00030282
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)