NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2DHV9N4T8FZXR45735XTKY
Run Details
Model:
DeepSeek V4 Flash
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
4.2s
Cost:
$0.000084
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
100.00%
Count dialogue tags
(details)
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
“I can’t believe they used the wrong sprinkles. For the mayor’s retirement cake. In *plain view* of the whole town council.” “They were pink. Pink is a perfectly acceptable sprinkle color.” “For a baby shower, maybe. But Melvin Hargrove has been the tax assessor for forty-three years. He deserves dignified blue.” “He deserves a slice without someone interrogating the icing. Hand me the spatula.” “You’re not listening. If the sprinkles are wrong, what else is wrong? The filing cabinet in the back office is crooked. Mrs. Drummond got her receipt written in green ink instead of black. It’s a *slippery slope*, I tell you.” “It’s a *bakery*. The only slope here is the one we’re about to slide down if you don’t let me finish this buttercream.” “Fine. But mark my words—this is how chaos starts. A wrong sprinkle here, a lime-green receipt there, and next thing you know, the town’s Christmas parade float is sponsored by the wrong feed store.” “Pass me the blue sprinkles.” “…They’re in the second drawer. Under the napkins. And you owe me an apology when they thank you tomorrow.”
created_at
"2026-04-25T13:34:04.088Z"
4/25/2026, 1:34:04 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
528
moderation_latency
(null)
generation_time
4089
tokens_prompt
81
tokens_completion
307
native_tokens_prompt
65
native_tokens_completion
267
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)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.00008386
router
(null)
provider_responses
0
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"7d1acd5f-a37e-4f50-9923-44fed937e9ee"
is_byok
false
latency
281
model_permaslug
"deepseek/deepseek-v4-flash-20260423"
provider_name
"DeepSeek"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777124044-8NgiYkNl6bSpRCulxjUJ"
session_id
(null)
api_type
"completions"
id
"gen-1777124044-OOpgyVIBu9gxfQWVv3Np"
upstream_id
"7d1acd5f-a37e-4f50-9923-44fed937e9ee"
total_cost
0.00008386
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)