NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2DZ92R99J0BYA9K0JE1SES
Run Details
Model:
DeepSeek V4 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
5.0s
Cost:
$0.000097
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
75.16%
Matches word count
(details)
7.84%
Dialogue to Total Word Ratio
(details)
41.4982%
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 flattened herself against the hedge, the sequined clown wig on her head catching the fading light like a disco ball that had given up on life. Bill was already halfway into the inflatable bouncy castle, which he insisted was the only logical entry point. “Are you sure this isn’t a mistake?” she hissed, watching a cluster of six-year-olds chase a piñata that looked suspiciously like their last getaway driver. Bill grunted, his legs tangled in purple vinyl. “It’s genius,” he whispered back. “They’ll never see us coming.” Molly popped a party blower in her mouth and surveyed the garden. A table groaned under a mountain of wrapped gifts—princess castles, remote-control cars, a glittery unicorn with a suspiciously large horn. She could almost smell the profit. Bill finally freed himself and dusted off his knees. “Okay, you create a diversion. I grab the haul.” Molly considered the very large mother holding a very large juice box. “What kind of diversion?” she asked. Bill pointed at the helium tank. “Fill that clown wig and float away. They’ll chase you for miles.” Molly sighed. “I hate this plan.”
created_at
"2026-04-25T13:41:24.188Z"
4/25/2026, 1:41:24 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
595
moderation_latency
(null)
generation_time
4936
tokens_prompt
77
tokens_completion
357
native_tokens_prompt
67
native_tokens_completion
313
native_tokens_completion_images
(null)
native_tokens_reasoning
62
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
0.00009702
router
(null)
provider_responses
0
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"f907f478-9700-4ac1-9633-44ce6ef57aaa"
is_byok
false
latency
289
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-1777124484-vmrfh2CslSUgWiSp2mZ7"
session_id
(null)
api_type
"completions"
id
"gen-1777124484-wbinJm6pHbXhL7S5dHxE"
upstream_id
"f907f478-9700-4ac1-9633-44ce6ef57aaa"
total_cost
0.00009702
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
75.16%
Matches word count
n/a
neededClean
false
words
187
7.84%
Dialogue to Total Word Ratio
Ratio: 22.63%, Deviation: 12.63%
neededClean
false
wordsTotal
190
wordsDialogue
43
41.4982%