NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2DHTFHSYV5YANNM4TBCP3N
Run Details
Model:
DeepSeek V4 Flash
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
4.7s
Cost:
$0.000094
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
48.8138%
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 adjusted her balaclava, a shimmering unicorn-patterned one she’d swiped from a craft fair. Bill frowned at the half-eaten bag of cheese puffs in his lap. “We’re adults. This is a children’s party.” “Which is why it’s genius,” Molly whispered. “No one expects a security system for a bouncy castle.” Bill crumpled the bag. “So the plan is: crash a five-year-old’s bash, shove the presents into that piñata, and walk out singing ‘Let it Go’?” “Exactly.” She pointed at the backyard. “The mother’s distracted by the clown. The father is on his third glass of ‘juice’ from a flask. We go in as ‘Party Patrol.’ I grab the Lego sets, you get the gift cards.” “What if we’re seen?” “We’ll say we’re with the balloon animal unit.” Bill snorted. “I don’t know how to make a balloon animal.” “Then practice. What’s easier? A giraffe or a getaway?” He stared at the bouncy castle, its inflatable walls wobbling with tiny screams. “A poodle. I’ll make a poodle. But if this goes south, I’m using you as a human shield.” Molly grinned. “Deal. Now follow my lead—and try not to step on the cake.”
created_at
"2026-04-25T13:34:03.253Z"
4/25/2026, 1:34:03 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
659
moderation_latency
(null)
generation_time
4625
tokens_prompt
77
tokens_completion
322
native_tokens_prompt
67
native_tokens_completion
303
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
0.00009422
router
(null)
provider_responses
0
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"fa4cbe2d-97bf-43cd-a01f-9cd17d9f91a7"
is_byok
false
latency
334
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-1777124043-VNEQ2KidskHwf4vdAS0R"
session_id
(null)
api_type
"completions"
id
"gen-1777124043-nzr2pyH3UvxMh6uUcT0f"
upstream_id
"fa4cbe2d-97bf-43cd-a01f-9cd17d9f91a7"
total_cost
0.00009422
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
97.63%
Matches word count
n/a
neededClean
false
words
193
0.00%
Dialogue to Total Word Ratio
Ratio: 71.57%, Deviation: 21.57%
neededClean
false
wordsTotal
197
wordsDialogue
141
48.8138%