NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5Z8HS5P4RK9C1W3PS9ZFB
Run Details
Model:
DeepSeek V3 (2024-12-26)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
11.0s
Cost:
$0.000293
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’s bells jingled softly as the door swung open, letting in a crisp autumn breeze. “Is that the infamous pumpkin spice latte cake? It smells divine.” “Fresh out of the oven and already half gone. Mrs. Higgins bought three slices for her tea party. You’re lucky there’s one left.” “Lucky? Or is this your way of buttering me up before you ask for a favor?” “Me? Buttering you up? Never. But now that you mention it, I could use some help tracking down whoever’s been stealing Mrs. Tully’s prized roses.” “Roses? That’s your mystery du jour? Shouldn’t you be investigating something more… sinister?” “Sinister? This is Willowbrook. The most sinister thing here is Mr. Grayson’s burnt scones.” “Fair point. Still, roses seem a bit… tame for someone like you.” “Tame? Have you met Mrs. Tully? She’s convinced it’s a conspiracy. Says the thief leaves glitter behind just to taunt her.” “Glitter? That’s oddly specific. Almost like someone wants to be noticed.” “Exactly. Which is why I suspect the culprit might be closer to home than she thinks.” “Closer to home, huh? You’re saying it’s personal?” “Very personal. And I have a feeling this glitter trail might lead right to her grandson’s art project.”
created_at
"2026-02-16T21:33:55.266527+00:00"
2/16/2026, 9:33:55 PM
model
"deepseek/deepseek-chat-v3"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
348
moderation_latency
(null)
generation_time
10988
tokens_prompt
81
tokens_completion
352
native_tokens_prompt
64
native_tokens_completion
306
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
0.00029282
router
(null)
provider_responses
0
id
"chatcmpl-R7iOyhR5JckpLICwhdHAigdk"
status
200
is_byok
false
latency
67
endpoint_id
"5294d55f-9012-496b-8f22-8cc919432dcd"
provider_name
"DeepInfra"
model_permaslug
"deepseek/deepseek-chat-v3"
api_type
"completions"
id
"gen-1771277623-0IumB1PXK7QuSP70Uib4"
upstream_id
"chatcmpl-R7iOyhR5JckpLICwhdHAigdk"
total_cost
0.00029282
cache_discount
(null)
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)