NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KBZ2QZVXZCQHGM0NJP8WPE
Run Details
Model:
DeepSeek V4 Flash 0731 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
7.4s
Cost:
$0.000116
Provider:
Parasail
Evaluation summary
Score
Evaluator
Details Link
9.61%
Matches word count
(details)
2.42%
Dialogue to Total Word Ratio
(details)
6.0144%
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 party was a fortress of pastel bunting and sticky-fingered chaos, and Molly surveyed it from behind a parked minivan, adjusting her ski mask over a pair of bunny ears. Bill, wedged into a too-small clown costume, fiddled with a lockpick shaped like a lollipop. “I still think we should’ve gone with the bouncy castle drop,” he muttered. Molly ignored him. The gift table stood unguarded, a mountain of shiny wrapping paper and parental negligence. She timed the piñata swing. Perfect. “Go low, grab the big ones, don’t trip over the balloons.” Bill nodded, then pointed at a toddler wielding a juice box like a grenade. “What about the kid?” Molly smirked. “He’s the lookout. I paid him in stickers.” They crept forward, past a magician doing card tricks, past a wailing baby, past a suspiciously large cupcake that mooed. Bill grabbed a present, then another, then froze as a small girl tugged his sleeve. “Are you the funny clown?” she asked. Bill glanced at Molly, who was already sprinting. “I’m the tax collector,” he said, and ran.
created_at
"2026-09-03T10:10:24.144Z"
9/3/2026, 10:10:24 AM
model
"deepseek/deepseek-v4-flash-20260731"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
250
moderation_latency
(null)
generation_time
7323
tokens_prompt
75
tokens_completion
358
native_tokens_prompt
146
native_tokens_completion
340
native_tokens_completion_images
(null)
native_tokens_reasoning
85
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
0.00011564
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788430224-FE7F2hUv84tdRUSkTtHs"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788430224-rCCDyxBW9nY9Iylsc6C2"
upstream_id
"6e803e1052ce44368cfc41794ff93c67"
provider_responses
0
endpoint_id
"3dc8bdba-8bee-42b8-9c9e-0d295c28e385"
id
"6e803e1052ce44368cfc41794ff93c67"
is_byok
false
latency
250
model_permaslug
"deepseek/deepseek-v4-flash-20260731"
provider_name
"Parasail"
status
200
total_cost
0.00011564
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Parasail"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
9.61%
Matches word count
n/a
neededClean
false
words
178
2.42%
Dialogue to Total Word Ratio
Ratio: 23.89%, Deviation: 13.89%
neededClean
false
wordsTotal
180
wordsDialogue
43
6.0144%