NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5CNNCJ958D3CGZDHE0A8B
Run Details
Model:
DeepSeek V3 (2025-03-24)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
12.6s
Cost:
$0.000299
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 as a rush of warm cinnamon air wafted out into the brisk morning. "You're here early. The cherry turnovers just came out of the oven—still too hot to touch." "Perfect. I need something to sweeten the blow of another round of budget cuts at the paper. You'd think the town’s only bakery burning down last year would’ve been front-page news for more than a week." "Maybe if you’d written more about the fire and less about the arson rumors, they’d have kept you on." "Rumors? The sprinklers were turned off, and half the flour was missing. That’s not a faulty wiring story." "Careful. Last person who asked too many questions about that fire ended up with a nasty ‘accident’ in their own kitchen." "Meaning?" "Meaning your usual order is on the house today." "That bad, huh?" "Let’s just say the cherry filling is the only thing that should be boiling over in this town." "Point taken. But if I ‘trip’ into a pie tomorrow, you’ll know why."
created_at
"2026-02-16T21:23:48.281321+00:00"
2/16/2026, 9:23:48 PM
model
"deepseek/deepseek-chat-v3-0324"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
400
moderation_latency
(null)
generation_time
12570
tokens_prompt
81
tokens_completion
279
native_tokens_prompt
67
native_tokens_completion
251
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
0.00029921
router
(null)
provider_responses
0
id
"6c09243d73c2a2abfb59ada07d748590"
status
200
is_byok
false
latency
400
endpoint_id
"3a816eb8-7a0b-4a9a-b497-e3a1efb349fc"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-chat-v3-0324"
api_type
"completions"
id
"gen-1771277014-w4L3lCBaIMyIpGvCu6af"
upstream_id
"6c09243d73c2a2abfb59ada07d748590"
total_cost
0.00029921
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)