NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2H6RT3FDX3022JP9FX1NQ5
Run Details
Model:
DeepSeek V4 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
29.4s
Cost:
$0.000121
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
60.28%
Matches word count
(details)
99.50%
Dialogue to Total Word Ratio
(details)
79.8877%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
“You sure about this, Bill?” Molly asked, adjusting her black ski mask. “A children’s party? That’s low, even for us.” “Low is high reward,” Bill said, fiddling with a laser pointer. “Look, the invitation says ‘Princess Rainbow’s 6th Birthday.’ The parents go all out—tablets, drones, even a pony once.” “A pony? How do we fence a pony?” “We don’t. We steal the gift bags. Each has a gift card worth at least fifty bucks. Twenty bags. That’s a grand. Easy.” “And the crying children? The tantrums? The birthday girl sobbing into her Rainbow Dash cake?” “That’s why we go during the magic show. The clown distracts them.” “A clown? Bill, I have a thing about clowns.” “You have a thing about everything. Fine. We go during the pinata. Kids are blindfolded with sticks. Perfect cover.” “So I wade into a mob of sugar-crazed six-year-olds swinging bats. While you—what?” “I crawl under the gift table. Snip the ribbon ties. You cause a diversion.” “Like what?” “I don’t know. Pretend to be a superhero. Burst through the bouncy castle. Yell ‘The presents are bewitched!’” Molly sighed. “I hate my life. But I hate my day job more. Fine. We go at three. But I’m keeping the clown makeup. For emergencies.” “Deal. Now pass the face paint.”
created_at
"2026-04-25T14:37:55.398Z"
4/25/2026, 2:37:55 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
13511
moderation_latency
(null)
generation_time
19216
tokens_prompt
77
tokens_completion
435
native_tokens_prompt
67
native_tokens_completion
398
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
0.00012082
router
(null)
provider_responses
0
endpoint_id
"934a69f9-bd54-474b-beca-24560f721e12"
is_byok
false
latency
56
model_permaslug
"deepseek/deepseek-v4-flash-20260423"
provider_name
"DeepInfra"
status
(null)
1
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"a2750552-b91b-495e-a420-dfb026a176d9"
is_byok
false
latency
270
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-1777127875-gx7oO34GZ6l2GaGoPrBZ"
session_id
(null)
api_type
"completions"
id
"gen-1777127875-YqYr2kEqYKOkJDq1GLrJ"
upstream_id
"a2750552-b91b-495e-a420-dfb026a176d9"
total_cost
0.00012082
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
60.28%
Matches word count
n/a
neededClean
false
words
215
99.50%
Dialogue to Total Word Ratio
Ratio: 92.66%, Deviation: 2.66%
neededClean
false
wordsTotal
218
wordsDialogue
202
79.8877%