NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2DQRDR51835MEGSV08W2H1
Run Details
Model:
DeepSeek V4 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
6.2s
Cost:
$0.000120
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
35.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
17.5011%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
Molly pressed her eye to the gap in the hedge, watching the bouncy castle inflate with a flatulent wheeze. Beside her, Bill fiddled with a purple party blower, occasionally letting its tongue unfurl in a sad little fizzle. The birthday tent was a riot of primary colors and shrieking children, a fortress of sticky fingers and sugar highs. “We go in when they do the piñata,” Molly whispered. “It’s the only window. Thirty seconds of chaos.” Bill licked his thumb, rubbed at a patch of grass stain on his black tracksuit. “And how do we carry out twelve gift bags and a tricycle without looking like off-brand Santas?” Molly pulled a folded rainbow bedsheet from her backpack. “We wear bliss. We wear sparkle. We become entertainers.” “I’m not juggling.” “You don’t have to. You just have to walk tall, wave, and look like you belong. Then we stuff the presents in the sheet, waddle to the van, and vanish.” Bill nodded slowly, then unfurled the blower. “Can I at least do the noise?” He gave it a sad, damp toot. Molly snatched it from his mouth. “No. That’s how we get caught.” She scanned the garden. A clown was juggling oranges. A unicorn piñata swung overhead, ready for its beating. Molly smiled. “Thirty seconds. That’s all we need.”
created_at
"2026-04-25T13:37:17.756Z"
4/25/2026, 1:37:17 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
516
moderation_latency
(null)
generation_time
6064
tokens_prompt
77
tokens_completion
426
native_tokens_prompt
67
native_tokens_completion
395
native_tokens_completion_images
(null)
native_tokens_reasoning
79
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
0.00011998
router
(null)
provider_responses
0
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"7625d8af-7007-42d2-9038-2e7761becc74"
is_byok
false
latency
271
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-1777124237-297Pie8fwR1RHeavdUfo"
session_id
(null)
api_type
"completions"
id
"gen-1777124237-5s1wGwWTr8vFZadwRl5o"
upstream_id
"7625d8af-7007-42d2-9038-2e7761becc74"
total_cost
0.00011998
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
35.00%
Matches word count
n/a
neededClean
false
words
218
0.00%
Dialogue to Total Word Ratio
Ratio: 43.38%, Deviation: 33.38%
neededClean
false
wordsTotal
219
wordsDialogue
95
17.5011%