NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2ED82FBMSTA3NCNV2XMZZ2
Run Details
Model:
DeepSeek V4 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
16.3s
Cost:
$0.000122
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.6885%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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
“I’m telling you, Bill, the bounce house is our Trojan horse.” Molly adjusted her fake horn-rimmed glasses. Bill stared at the party supply list. “We’re stealing presents from five-year-olds. There’s no dignity in a bounce house.” “Dignity doesn’t pay for my laser-cutter upgrade.” She tapped the map. “We roll in as ‘Uncle Bob’ and ‘Aunt Marge’—obnoxious relatives everyone ignores.” Bill sighed. “And my job?” “You’re the barf decoy.” “The what?” “When the bouncy castle spring leaks, pretend to be queasy. All attention on you. I grab the gift table.” “I have to simulate vomiting? In front of actual children?” “Method acting, Bill. You’ll get an award.” He rubbed his temples. “What if they smell a rat?” “We’re stealing Hello Kitty backpacks, not the Crown Jewels.” “There’s a piñata,” he muttered. “I love piñatas.” “No. Stay focused. After the cake cutting, I swap the presents with these.” She opened a bag of identical boxes filled with rocks. Bill peeked inside. “That’s duct-tape weight. They’ll know.” “By then we’re gone. Plan B: if caught, cry and say we’re from the IRS.” “Crying children, crying IRS agents—this is a nightmare.” Molly grinned. “Welcome to high-risk birthday security.”
created_at
"2026-04-25T13:49:01.907Z"
4/25/2026, 1:49:01 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
610
moderation_latency
(null)
generation_time
6085
tokens_prompt
77
tokens_completion
428
native_tokens_prompt
67
native_tokens_completion
401
native_tokens_completion_images
(null)
native_tokens_reasoning
78
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
0.00012166
router
(null)
provider_responses
0
endpoint_id
"934a69f9-bd54-474b-beca-24560f721e12"
is_byok
false
latency
79
model_permaslug
"deepseek/deepseek-v4-flash-20260423"
provider_name
"DeepInfra"
status
(null)
1
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"b0540ea4-7db6-45d2-b6ac-f2cf1b3bfeec"
is_byok
false
latency
277
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-1777124941-9htdhQ3ppVuDES6wPAvN"
session_id
(null)
api_type
"completions"
id
"gen-1777124941-JXKrHpYMoN0lWxO20jFv"
upstream_id
"b0540ea4-7db6-45d2-b6ac-f2cf1b3bfeec"
total_cost
0.00012166
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.38%
Matches word count
n/a
neededClean
false
words
195
0.00%
Dialogue to Total Word Ratio
Ratio: 79.60%, Deviation: 29.60%
neededClean
false
wordsTotal
201
wordsDialogue
160
49.6885%