NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-10-01M25DJT48TVJ5ZVAYH77GMV8N
Run Details
Model:
DeepSeek V4.1 Flash (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
13.4s
Cost:
$0.001902
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.99%
Dialogue to Total Word Ratio
(details)
99.9968%
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 and Bill, two thieves with the moral flexibility of wet cardboard, crouched behind a hedge outside the Sunshine Palace. Inside, thirty shrieking children celebrated twins' birthday. Presents formed a gaudy mountain near the bouncy castle. Molly checked her watch. "Balloons are the alarm?" Bill nodded. "Balloons are the alarm. Cake first, presents second." "And the piƱata?" "Ignore it. It bites. Please." Bill unfolded a crayon-drawn map. The party's security included a clown with a whistle, a grandmother with a handbag, and a toddler who had already bitten two adults. Molly proposed entering as magicians. Bill preferred the caterer's entrance, but the caterer was his vengeful ex-wife. They settled on crawling through the ball pit. The ball pit, unfortunately, contained a sleeping pug. The pug contained no useful plan. Molly whispered that they would distract the children with a fake unicorn. Bill would bag every gift, including the lumpy one that ticked. They synchronized watches, then remembered neither owned a watch. Somewhere inside, a child screamed with joy. Molly flinched. Bill grinned. This was either their masterpiece or the fastest way to wind up in birthday-party prison. The plan was stupid and glittery, which was exactly why it might work.
created_at
"2026-09-10T10:24:59.02Z"
9/10/2026, 10:24:59 AM
model
"deepseek/deepseek-v4.1-flash-20260910"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
915
moderation_latency
(null)
generation_time
13345
tokens_prompt
75
tokens_completion
3161
native_tokens_prompt
93
native_tokens_completion
3147
native_tokens_completion_images
(null)
native_tokens_reasoning
2864
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"
service_tier
(null)
usage
0.00190215
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1789035899-O5CACT6xZ27FeR3brHK6"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1789035899-PErmzpzRKE6Fzpmbt4mE"
upstream_id
"7461bace-b453-4cc9-bedc-8f7b38119d8c"
provider_responses
0
endpoint_id
"fd104bc8-535a-4d31-a847-a8e402e86a02"
id
"7461bace-b453-4cc9-bedc-8f7b38119d8c"
is_byok
false
latency
335
model_permaslug
"deepseek/deepseek-v4.1-flash-20260910"
provider_name
"DeepSeek"
status
200
total_cost
0.00190215
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
99.99%
Dialogue to Total Word Ratio
Ratio: 10.89%, Deviation: 0.89%
neededClean
false
wordsTotal
202
wordsDialogue
22
99.9968%