NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2DGE0MXSBFFNQ0XGMYAAK1
Run Details
Model:
DeepSeek V4 Pro
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
7.6s
Cost:
$0.000249
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
The little brass bell above the door had barely stopped shivering when the first words cut through the warm, yeast-scented air. “You’re hiding a body in the walk-in freezer, aren’t you?” “Don’t be ridiculous. It’s strictly for the bulk butter and the seasonal fruit compotes. The health inspector would have a field day.” “Oh, so the health inspector is the line, not the actual, you know, murder. That’s comforting. Is that why the éclairs are half-price? A little ‘sorry-for-the-inconvenience-of-a-crime-scene’ discount?” “The éclairs are half-price because you distracted me, and I forgot the salt in the first batch. Not everything is a conspiracy. Hand me the piping bag.” “Fine. But explain the single yellow crime-scene glove on the counter next to the sprinkle rack. Very chic, very fashionable, very ‘I-just-finished-something-nefarious.’" “That’s an oven mitt. An oven mitt with a whimsical sunflower print. I dropped the other one behind the industrial mixer. Now, are you here to interrogate me or are you going to buy a croissant?”
created_at
"2026-04-25T13:33:17.721Z"
4/25/2026, 1:33:17 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1063
moderation_latency
(null)
generation_time
7551
tokens_prompt
81
tokens_completion
289
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)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.000249255
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"a5387fe5-d088-468e-b472-77e334dfe4e0"
is_byok
false
latency
277
model_permaslug
"deepseek/deepseek-v4-pro-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-1777123997-b5gpfmI2L0MesHeobWDU"
session_id
(null)
api_type
"completions"
id
"gen-1777123997-szYM1Yr9j0Vz5AT1xJ5x"
upstream_id
"a5387fe5-d088-468e-b472-77e334dfe4e0"
total_cost
0.000249255
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)