NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2E88B73M3XFZK6Y5XVZR9N
Run Details
Model:
DeepSeek V4 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
6.1s
Cost:
$0.000121
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 bell above the bakery door chimed, and the scent of cinnamon and sugar swirled with the cold draft. “You’re here early. Couldn’t sleep again?” “The strudel’s been gone by nine every morning this week. I wanted to be sure.” “It’s not the strudel you’re after, is it?” A pause, the soft thud of a pastry box being set on the counter. “I saw her last night. In the alley behind the library.” “You saw who?” “Eleanor. With her apron still on. She was talking to someone, but I couldn’t see their face. She looked… scared.” “Eleanor hasn’t worked here in three years. You sure it was her?” “Positive. She had that same silver locket, the one with the tiny rose. The one she never takes off.” The bell jingled again, and footsteps hesitated at the door. “Speaking of—is that her? Ordering at the register?” “No. That’s just Martha from the hardware store. Eleanor wouldn’t dare show her face in here now. Not after last time.” “Last time? What happened last time?” A long exhale, the squeak of a stool. “That’s the thing, dear. Nobody remembers. And that’s exactly what bothers me.”
created_at
"2026-04-25T13:46:18.348Z"
4/25/2026, 1:46:18 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
644
moderation_latency
(null)
generation_time
6014
tokens_prompt
81
tokens_completion
453
native_tokens_prompt
65
native_tokens_completion
399
native_tokens_completion_images
(null)
native_tokens_reasoning
112
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
0.00012082
router
(null)
provider_responses
0
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"b4d1188e-7f2f-4f90-a861-2e627fac7c45"
is_byok
false
latency
272
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-1777124778-EfnAxxXpC7e3XejhewNE"
session_id
(null)
api_type
"completions"
id
"gen-1777124778-EvN4jyS6k3jyiLHRA17k"
upstream_id
"b4d1188e-7f2f-4f90-a861-2e627fac7c45"
total_cost
0.00012082
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)