NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5D79598MT5MJZJ2KETWS6
Run Details
Model:
DeepSeek V3 (2025-03-24)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
22.0s
Cost:
$0.000212
Provider:
DeepInfra
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 bakery smelled of cinnamon and warm sugar, the bell above the door jingling softly as it swung shut. "You're late." "I know. The cat got out again." "That cat has a sixth sense for inconvenient timing." "Tell me about it. By the time I caught her, she was halfway to Mrs. Whitaker's rose bushes." "You didn’t let her near those roses, did you? You know how Mrs. Whitaker feels about trespassers—furry or otherwise." "Don’t worry, I scooped her up before disaster struck. But enough about the cat. What’s the emergency?" "Emergency might be too strong a word. But someone left this on the counter." "A note?" "More like a threat. ‘Stop baking the truth.’" "That’s… oddly poetic for a threat." "Poetic or not, it’s unsettling. And it’s written in frosting." "Frosting? So it’s someone who knows their way around a bakery." "Exactly. Which means the culprit is probably closer than we think." "Well. That’s one way to ruin a perfectly good morning." "Tell me about it. Pass the coffee."
created_at
"2026-02-16T21:24:15.061867+00:00"
2/16/2026, 9:24:15 PM
model
"deepseek/deepseek-chat-v3-0324"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
566
moderation_latency
(null)
generation_time
21962
tokens_prompt
81
tokens_completion
290
native_tokens_prompt
64
native_tokens_completion
262
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
32
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
0.00021246
router
(null)
provider_responses
0
id
"chatcmpl-RHRXyhgA8frgP9jUT7u0F2Xs"
status
200
is_byok
false
latency
69
endpoint_id
"820376cb-f110-4d56-ab52-5bd6ca269420"
provider_name
"DeepInfra"
model_permaslug
"deepseek/deepseek-chat-v3-0324"
api_type
"completions"
id
"gen-1771277032-rMM7EngHLVczcwxU3GCJ"
upstream_id
"chatcmpl-RHRXyhgA8frgP9jUT7u0F2Xs"
total_cost
0.00021246
cache_discount
0.00000208
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)