NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2JE1C1NEC5HPKCW5JEBJYB
Run Details
Model:
DeepSeek V4 Pro
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
7.1s
Cost:
$0.001338
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 warm, yeasty air wrapped around the two figures like a familiar blanket, the only sound the gentle hum of a refrigerated display case. “You can’t seriously think old Mr. Henderson had anything to do with it. The man uses a walker.” “A very sturdy walker. Aluminum frame. Could easily have delivered a blunt-force trauma.” “To a jar of raspberry preserves? It wasn’t a murder weapon, it was the thing that was stolen. Along with a sourdough loaf and a half-dozen cheese scones. That’s not a crime of passion, that’s a crime of… peckishness.” “It’s the principle of the thing. The lock on the back door was jimmied with a professional touch. A simple bread heist doesn't explain the precision.” “The ‘professional touch’ was a credit card slipped between the latch. I did it myself last Tuesday when I forgot my keys. And besides, look. A trail of powdered sugar, leading right from the display case.” “Straight to the alley. The perpetrator is long gone.” “Not to the alley. Look again. It circles the case, then stops right at the corner booth. The one where Beatrice always sits. The woman who swore off carbs for her New Year’s resolution.”
created_at
"2026-04-25T14:59:22.119Z"
4/25/2026, 2:59:22 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
434
moderation_latency
(null)
generation_time
6728
tokens_prompt
81
tokens_completion
316
native_tokens_prompt
65
native_tokens_completion
273
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
0.0013377
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
is_byok
false
latency
267
model_permaslug
"deepseek/deepseek-v4-pro-20260423"
provider_name
"DeepSeek"
status
429
1
endpoint_id
"13bda129-f8a6-4a60-b1db-98082e5f7ccd"
id
"ogZpUmM-6z2FuN-9f1e361105941690"
is_byok
false
latency
430
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-1777129162-IcbrW3EczagxDRqC5Mem"
session_id
(null)
api_type
"completions"
id
"gen-1777129162-u6p2iNM819FmjLA4rBgC"
upstream_id
"ogZpUmM-6z2FuN-9f1e361105941690"
total_cost
0.0013377
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)