NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2HG8GRBFJSQ7DXW17A95TV
Run Details
Model:
DeepSeek V4 Flash
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
4.9s
Cost:
$0.000088
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
46.8248%
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 crack in the fence, watching the bouncy castle inflate with an asthmatic wheeze. Bill, balancing on a recycling bin, squinted at a pink slip of paper. “The parents’ social media feed said the loot pile starts forming at 2:15.” The list fluttered in his grip. “We hit the gazebo, grab the haul, and disappear into the hedge maze before the first round of ‘Pin the Tail’—which I’m told is a chaotic mess.” Molly grunted, pulling a pair of fake-owl glasses from her pocket. “My distraction is flawless.” Bill exhaled. “You’re going to pretend to be an emotionally disturbed magician again?” “It worked last time.” “We were evicted from that retirement home, Molly. They still have flashbacks.” From inside the garden, a child’s shriek of pure, concentrated joy pierced the air. Bill’s shoulders sagged. “I’m having second thoughts.” Molly snorted. “Don’t get soft on me. That’s a mountain of Pokémon cards and unopened craft kits.” Bill looked at her, then at the mound of glitter-wrapped presents being stacked under the canopy. “Fine. But if anyone asks for a balloon animal, I’m locking you in the car.”
created_at
"2026-04-25T14:43:06.396Z"
4/25/2026, 2:43:06 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
727
moderation_latency
(null)
generation_time
4853
tokens_prompt
77
tokens_completion
310
native_tokens_prompt
67
native_tokens_completion
281
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
0.00008806
router
(null)
provider_responses
0
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"1909a64c-11f8-4763-b05c-886d647e7642"
is_byok
false
latency
273
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-1777128186-hyRMY3seIwFXsU16pJ5L"
session_id
(null)
api_type
"completions"
id
"gen-1777128186-nUxPtbVnI4YtywAmv9nw"
upstream_id
"1909a64c-11f8-4763-b05c-886d647e7642"
total_cost
0.00008806
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
93.65%
Matches word count
n/a
neededClean
false
words
191
0.00%
Dialogue to Total Word Ratio
Ratio: 54.40%, Deviation: 44.40%
neededClean
false
wordsTotal
193
wordsDialogue
105
46.8248%