NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2EEQVDHGZNSXTPYN0TAA3A
Run Details
Model:
DeepSeek V4 Flash
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
15.4s
Cost:
$0.000086
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 still say it’s odd that the church raffle started the same week as the fire.” “Thyme and butter don’t mix. You’re reading too much into a flour bin left too close to the gas line.” “Margaret’s flour bin has been in that exact spot for forty years. She even named it. Calls it ‘Norbert.’” A pause, muffled by the crinkle of a wax-paper bag. “She named her flour bin.” “She named the whole bakery’s inventory. You didn’t know? That rolling pin over there is ‘Barbara.’ Now, answer me this—if Norbert had been there that long, and Mrs. Pendleton’s curtains were always damp from the steam, why didn’t he catch fire before?” “Maybe someone moved him.” “Exactly. Someone who wanted to make sure the fire started *after* the raffle tickets were sold. For insurance, or for something else.” A soft thud of a fresh loaf being set on the counter. “That’s why I’m sticking with scones today. They don’t keep secrets.” “All right, but I’m buying a cruller. If I’m going to solve a mystery, I need sugar.” The bell above the door jingled. No one looked up.
created_at
"2026-04-25T13:49:50.835Z"
4/25/2026, 1:49:50 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
949
moderation_latency
(null)
generation_time
4689
tokens_prompt
81
tokens_completion
303
native_tokens_prompt
65
native_tokens_completion
275
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
0.0000861
router
(null)
provider_responses
0
endpoint_id
"934a69f9-bd54-474b-beca-24560f721e12"
is_byok
false
latency
53
model_permaslug
"deepseek/deepseek-v4-flash-20260423"
provider_name
"DeepInfra"
status
(null)
1
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"f3befed9-4a08-4969-a505-5eec84fa4717"
is_byok
false
latency
687
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-1777124990-o5kKP9I151B4QjHD78gj"
session_id
(null)
api_type
"completions"
id
"gen-1777124990-pa6dNJyWMm4wGxO3hUSh"
upstream_id
"f3befed9-4a08-4969-a505-5eec84fa4717"
total_cost
0.0000861
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)