NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2JDPADYG99SACZ7XP4MKWX
Run Details
Model:
DeepSeek V4 Pro (Reasoning)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
6m 53s
Cost:
$0.037148
Provider:
Together
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 bakery's screen door had stopped its creaking an hour ago, but the two inside hadn't noticed. The air was thick with the smell of burnt sugar and something elseāfear. A display of croissants sat untouched, the morning rush forgotten. A coffee cup sat between them, the cream forming a skin on the surface. You heard about the footprints in the flour? Right outside the back door. A hand twisted a napkin into a tight coil. Footprints? From what? From who. And whoever it was, they were here late. The security light never came on. Are you sure? Could've been a stray cat. Or the wind. It's been gusty lately. They left boot prints, size ten. Besides, the back door was found ajar. I always lock it. You know that. But nothing's missing? The cash, yesterday's receipts? The pie weights? Nothing missing. But something was left. Left what? A single red rose. Placed on the stand mixer. Like a calling card. With a note: 'I know your recipe.' The quiet returned, thicker than rising dough. Beyond the window, the clock tower struck nine, muffled by the glass. Outside, a car passed slowly, its engine a low growl that hung in the air long after it disappeared. The morning had changed, and they both knew it.
created_at
"2026-04-25T15:00:07.557Z"
4/25/2026, 3:00:07 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
35519
moderation_latency
(null)
generation_time
355566
tokens_prompt
81
tokens_completion
8365
native_tokens_prompt
144
native_tokens_completion
8374
native_tokens_completion_images
(null)
native_tokens_reasoning
8044
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
0.037148
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
is_byok
false
latency
272
model_permaslug
"deepseek/deepseek-v4-pro-20260423"
provider_name
"DeepSeek"
status
429
1
endpoint_id
"13bda129-f8a6-4a60-b1db-98082e5f7ccd"
id
"ogZpiFx-6z2FuN-9f1e372d0018cf9b"
is_byok
false
latency
35519
model_permaslug
"deepseek/deepseek-v4-pro-20260423"
provider_name
"Together"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777129207-BnRlxO6unZl4e51lyVH5"
session_id
(null)
api_type
"completions"
id
"gen-1777129207-edZ1fwmRpwJzYf9MqNFg"
upstream_id
"ogZpiFx-6z2FuN-9f1e372d0018cf9b"
total_cost
0.037148
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Together"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)