NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2FGMYE3YG2BATTANB4H2G5
Run Details
Model:
DeepSeek V4 Pro
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
1m 15s
Cost:
$0.001303
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 smell of cinnamon and yeast hung thick and sweet in the air, a gentle shield against the gray drizzle outside the bakery window. A cooling rack held a battalion of muffins, their domed tops glistening with butter. “You heard about the library’s rare book fund? Disappeared. Vanished like one of Doris’s lemon tarts at a church social.” “I heard Doris makes a lemon tart that could drive a person to crime, but I doubt it’s connected. It was just there yesterday, in the locked case. The ledger, too. The lock wasn’t broken, you know.” “So, a ghost with a sweet tooth and a head for numbers? I don’t buy it. I saw Eleanor Peabody in here earlier, loading up on scones. Looked like a woman who’d just come into money.” “Eleanor’s been loading up on scones since her cat, Mr. Darcy, went missing in ’09. It’s comfort eating, not a spending spree funded by library theft. Besides, everyone knows the only thing Eleanor steals is extra napkins.” “Well, it’s someone. And I intend to find out who, just as soon as I finish this bear claw. A detective needs sustenance.”
created_at
"2026-04-25T14:08:21.969Z"
4/25/2026, 2:08:21 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
37720
moderation_latency
(null)
generation_time
74243
tokens_prompt
81
tokens_completion
291
native_tokens_prompt
65
native_tokens_completion
265
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
0.0013025
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
"ogZYo5Q-6z2FuN-9f1deb5b13e0ed35"
is_byok
false
latency
37720
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-1777126101-nPzfEFf8G5pjqu9Zn0kj"
session_id
(null)
api_type
"completions"
id
"gen-1777126101-0BhNLNtgnceIDUQ1W468"
upstream_id
"ogZYo5Q-6z2FuN-9f1deb5b13e0ed35"
total_cost
0.0013025
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)