NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5DG2XGYZNT6XBZAHDQJ4E
Run Details
Model:
DeepSeek V3.1
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
18.2s
Cost:
$0.000200
Provider:
SambaNova
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 welcome. "Is that my favorite critic?" "In the flour-dusted flesh. I’m on a fact-finding mission regarding the state of your cherry scones." "They’re just coming out of the oven. You’re early. Trying to catch me with yesterday’s goods?" "A good reporter never reveals her sources. Now, are you going to make me suffer, or do I get a sample?" "A sample, and my undying gratitude if you can solve a little mystery for me. Someone’s been leaving small bouquets of lavender on the back step every morning this week." "Lavender? How quaint. Any suspects?" "Not a one. It’s very sweet, but a touch unnerving. No note, no explanation. Just… lavender." "Sounds like a secret admirer. Or perhaps a very polite critic of your pastry. Have you tried staying late to catch them?" "And miss my beauty sleep? I’m a baker, not a private eye. I was hoping you had a theory. You’re good with the town’s gossip." "I’ll add it to my list of investigations. But first, my scone. This mystery requires fortification."
created_at
"2026-02-16T21:24:20.497136+00:00"
2/16/2026, 9:24:20 PM
model
"deepseek/deepseek-chat-v3.1"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1715
moderation_latency
(null)
generation_time
18100
tokens_prompt
100
tokens_completion
282
native_tokens_prompt
65
native_tokens_completion
254
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
0.00020025
router
(null)
provider_responses
0
status
429
is_byok
false
latency
53
endpoint_id
"012f7d1f-23d4-4d03-9aa3-432d8ad82757"
provider_name
"DeepInfra"
model_permaslug
"deepseek/deepseek-chat-v3.1"
1
id
"24852149-96b0-473e-aad7-24d2947bb84c"
status
200
is_byok
false
latency
1715
endpoint_id
"1dda4bb9-c626-4816-bb54-99665323fef0"
provider_name
"SambaNova"
model_permaslug
"deepseek/deepseek-chat-v3.1"
api_type
"completions"
id
"gen-1771277041-kKeKdlMlvT44legHbsBg"
upstream_id
"24852149-96b0-473e-aad7-24d2947bb84c"
total_cost
0.00020025
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SambaNova"
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)