NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2DVAPVX0WFZGAHM5BBSMVY
Run Details
Model:
DeepSeek V4 Flash
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
3.9s
Cost:
$0.000075
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 jingled, and a gust of cinnamon-scented air swirled around the display case. “They’re not even trying to hide it anymore.” “The scones? I know. The cranberry ones are practically crumbling just from looking at them.” “I meant the note. Tucked under the register, plain as day. ‘Meet me where the second oven used to be.’ What second oven?” “Used to be. That’s the trick of it. Old Mrs. Gable had two, remember? They bricked one up after the fire of ’69. Her secret recipe was supposed to be inside.” “And now someone thinks it’s worth a letter? Sounds like a ghost story for tourists.” “Or a warning. Look, I’m not going near that wall. You can’t unsee a bricked-up oven at midnight.” “Fine. But if you’re wrong, and that note’s about the new lemon tart recipe, I’m eating both of yours.” “Deal. But bring a flashlight. And don’t blame me if the buttercream gets weird.”
created_at
"2026-04-25T13:39:14.784Z"
4/25/2026, 1:39:14 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
580
moderation_latency
(null)
generation_time
3730
tokens_prompt
81
tokens_completion
261
native_tokens_prompt
65
native_tokens_completion
236
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
0.00007518
router
(null)
provider_responses
0
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"316dbb15-581f-49c7-b00e-91908236dd79"
is_byok
false
latency
284
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-1777124354-N2IQYSYTwETrz0kogvim"
session_id
(null)
api_type
"completions"
id
"gen-1777124354-92ta9DgyppFT7jHm9DyU"
upstream_id
"316dbb15-581f-49c7-b00e-91908236dd79"
total_cost
0.00007518
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)