NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2E68SN4MSPK1JHRGJK0JJP
Run Details
Model:
DeepSeek V4 Pro
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
10.0s
Cost:
$0.000291
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
14.30%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
25.5447%
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
“Right, Molly, talk me through it. A children’s party. We’re not monsters.” “Bill, we’re liberators. Little Timmy doesn’t need a seventh dinosaur coloring book. He’s six. His artistic vision is still mostly drool-based.” “So we’re going in as what, exactly?” “Bubbles the Clown and Giggles the Elf.” “I’m not wearing tights, Molly. I’m a career criminal. There are standards for legwear.” “Fine, you’re Bubbles, I’m Giggles. The bowtie will take attention away from your shifty eyes. The plan is elegant. We arrive, we juggle, we announce a magical present-mustering parade to the bouncy castle. The little sugar-fueled goblins form a conga line, we stack the goods, and we vanish in the ensuing juice-box riot.” “What’s the contingency for a crier?” “A balloon animal. A tragically malformed poodle destroys their will to fight.” “And the parents?” “Exhausted husks, Bill. They’ll see two hired entertainers loading a sack of brightly colored boxes and feel only a profound, existential relief. We’re practically philanthropists.” “…And the cake?” “We take the cake. It’s a sheet cake, Bill. They’ll never even miss a corner piece.”
created_at
"2026-04-25T13:45:13.273Z"
4/25/2026, 1:45:13 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
855
moderation_latency
(null)
generation_time
9985
tokens_prompt
77
tokens_completion
322
native_tokens_prompt
67
native_tokens_completion
301
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
0.000291015
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"c550e14b-6489-4c79-8ddf-5c67f2d416c7"
is_byok
false
latency
269
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-1777124713-0G5hzYgKjPd6hdziA3pG"
session_id
(null)
api_type
"completions"
id
"gen-1777124713-5U76yefjCvsiir8KC8OG"
upstream_id
"c550e14b-6489-4c79-8ddf-5c67f2d416c7"
total_cost
0.000291015
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
14.30%
Matches word count
n/a
neededClean
false
words
179
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
183
wordsDialogue
183
25.5447%