NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2HJ9DDHMPEWG1ENZ0DFTXK
Run Details
Model:
DeepSeek V4 Flash
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
5.0s
Cost:
$0.000093
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
47.9934%
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
Molly tapped a glittery pink invitation against her palm. “Okay, run it by me again.” Bill adjusted his ski mask, which was damp and smelled like old socks. “We waltz in at three. You’re ‘Auntie Sparkles’ from the clown college. I’m your assistant, ‘Beeps the Balloon Boy.’” “That’s your heavy lifting?” Molly snorted. “What if someone asks for a giraffe?” “I fake a hernia. Look, the real plan is the scooter.” He pointed to a purple Razor with streamers on the handlebars. “I stuff the loot in the basket, we ride right out the fire exit.” “Through a dozen sugared-up seven-year-olds?” She raised an eyebrow. “Their senses are heightened. They can smell a loose Jolly Rancher from three blocks.” “They’ll be distracted by the piñata. I’ll bribe the birthday kid.” “With what, your dignity?” Bill sighed. “Earplugs. A fidget spinner. Look, it’s tight, but the gift pile is a goldmine—unregistered Elsa dolls, untraceable Lego sets. The fence loves a unicorn that still farts glitter.” Molly folded the invitation. “Fine. But when we’re surrounded by a mob of shrieking toddlers demanding we do the chicken dance, you’re the one doing the time.”
created_at
"2026-04-25T14:44:12.849Z"
4/25/2026, 2:44:12 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
588
moderation_latency
(null)
generation_time
4863
tokens_prompt
77
tokens_completion
329
native_tokens_prompt
67
native_tokens_completion
300
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
0.00009338
router
(null)
provider_responses
0
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"b2c794a2-c78f-4ab1-8fd6-a64dc06c6bb8"
is_byok
false
latency
420
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-1777128252-o0QWY4hPpf4LqudHKnNU"
session_id
(null)
api_type
"completions"
id
"gen-1777128252-eGW2oNo52uzSjd2VhQr6"
upstream_id
"b2c794a2-c78f-4ab1-8fd6-a64dc06c6bb8"
total_cost
0.00009338
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
95.99%
Matches word count
n/a
neededClean
false
words
192
0.00%
Dialogue to Total Word Ratio
Ratio: 76.92%, Deviation: 26.92%
neededClean
false
wordsTotal
195
wordsDialogue
150
47.9934%