NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2G70KFBCFP51XTVA1TJMGQ
Run Details
Model:
DeepSeek V4 Flash
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
4.1s
Cost:
$0.000079
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
0.03%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0152%
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
The inflatable bouncy castle loomed like a polyester Everest. Molly, wedged behind a hedge, squinted at the marquee. "Gift table's a soft target. Between the face painting and the magician's sad rabbit, we've got a four-minute window." Bill adjusted his fake mustache, which was already peeling. "Four minutes? That's less time than it takes to blow up one of those long balloon dogs." Molly pointed. "You start with the unicorn piƱata. Distract the ankle-biters while I bag the presents. Remember, no snot, no tears, no kicking." "For the record, I'm allergic to glitter and enthusiasm." A child screamed nearby. Bill flinched. "Plan B: if the magician pulls a sword from a hat, I'm using you as a human shield. I mean it." Molly rolled her eyes. "Just get over there and pretend you're the dad who's 'really trying.'" Bill shuffled forward, waving a lollipop like a white flag. "Alright, little people," he croaked, his voice cracking. "Who wants to see a balloon giraffe that looks more like a deformed pickle?"
created_at
"2026-04-25T14:20:34.803Z"
4/25/2026, 2:20:34 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
559
moderation_latency
(null)
generation_time
3998
tokens_prompt
77
tokens_completion
265
native_tokens_prompt
67
native_tokens_completion
250
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
0.00007938
router
(null)
provider_responses
0
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"dca03231-c61b-4d4c-8669-cebe35b3dba5"
is_byok
false
latency
283
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-1777126834-reI9x4AU59FelMOUanuh"
session_id
(null)
api_type
"completions"
id
"gen-1777126834-jWK4CE29Kn4QTZcRtJWX"
upstream_id
"dca03231-c61b-4d4c-8669-cebe35b3dba5"
total_cost
0.00007938
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
0.03%
Matches word count
n/a
neededClean
false
words
170
0.00%
Dialogue to Total Word Ratio
Ratio: 68.60%, Deviation: 58.60%
neededClean
false
wordsTotal
172
wordsDialogue
118
0.0152%