NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2J6BX2VKKGQCJT7RDKCNJM
Run Details
Model:
DeepSeek V4 Pro
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
34.5s
Cost:
$0.000346
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
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
Molly squinted through the binoculars at a suburban house that looked like a unicorn had vomited rainbows all over it. She lowered the lenses and rubbed her eyes with the heels of her hands. “I’ve lost the ability to perceive the colour beige,” Molly said. Bill, wedged beside her in the stolen ice cream van, was applying clown makeup using the rearview mirror. His attempt at a cheerful grin made him look like a man recovering from a startled lip surgery. “Beige is for people who pay for gifts. My honking nose is on crooked. Do I look trustworthy?” Bill asked. “You look like a man who lures children with a single tear and a vague sense of doom,” she said. “Perfect. What’s our entry vector?” She consulted a purple glitter-encrusted invitation they’d lifted from a mom in a parking lot. “According to this, the entertainment arrives via the side gate. That’s us. You’re Bumbles the Clown, I’m your exhausted handler.” “And what’s Bumbles’ defining characteristic, artistically speaking?” he asked, ruffling a polka-dotted neck ruff. “You trip over things,” she said. “A lot. That’s the chaos. While you’re pratfalling through the piñata, I’m the distracted adult wheeling a very large, very empty gift-wrapped box toward the present table.” Bill practiced a sorrowful expression. “Pity. I was hoping to debut my mime act. A man trapped in a box of his own existential greed.” “Save the pathos for the birthday boy. He’s turning five. He’ll think you’re a silent fart joke,” she said.
created_at
"2026-04-25T14:55:32.095Z"
4/25/2026, 2:55:32 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1384
moderation_latency
(null)
generation_time
12655
tokens_prompt
77
tokens_completion
417
native_tokens_prompt
67
native_tokens_completion
364
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
0.000345825
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"c391e1e3-8b36-4b67-8cb0-49c5b7f5df8c"
is_byok
false
latency
420
model_permaslug
"deepseek/deepseek-v4-pro-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-1777128932-vEmaCoG7PueIjoAV9QOQ"
session_id
(null)
api_type
"completions"
id
"gen-1777128932-csNuyxbU1mEowOtTz24R"
upstream_id
"c391e1e3-8b36-4b67-8cb0-49c5b7f5df8c"
total_cost
0.000345825
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
252
0.00%
Dialogue to Total Word Ratio
Ratio: 57.25%, Deviation: 47.25%
neededClean
false
wordsTotal
255
wordsDialogue
146
0.0000%