NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2G7ET86S1C5P2BMWHKPKVD
Run Details
Model:
DeepSeek V4 Pro
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
12.0s
Cost:
$0.000355
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
18.3940%
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
“Molly, I’m looking at the blueprints. They’ve got a Bouncy Castle on the east flank. That’s a tactical nightmare.” “Bill, it’s not a flank, it’s a rented inflatable. We treat it as a diversionary asset.” “A diversion from what? Face-painting tigers? I don't do glitter, Molly. It clings.” “You’ll wear the clown suit, you’ll take the glitter, and you’ll secure the loot. Now, the birthday boy, Kevin, is turning six. He’s our mark.” “A six-year-old is the primary security layer? What’s he gonna do, gum me to death?” “Worse. Juice box in the face. Sticky. Incapacitating. We bypass him using the decoy.” “Please don’t tell me we’re using the singing unicorn.” “We’re using the singing unicorn. You press the hoof, it belts out a show tune, the little gremlins swarm it like ants on a sugar cube, and I back the van up to the gift table.” “What about his mother? Carol? She was a state trooper. She retains a situational awareness that’s frankly terrifying.” “Leave Carol to me. I’ve developed a rapport. I told her my organic gluten-free cake pops are in the car. She’ll let me out the back gate with a forklift if she thinks it’s organic.” “And the silent alarm disguised as a play-pretend crumb-catcher vacuum?” “Disabled. Replaced the batteries with crayons. Bill, are you in or are you out?” “I’m in. But I want the unicorn’s head when this is over. As a trophy.”
created_at
"2026-04-25T14:20:51.267Z"
4/25/2026, 2:20:51 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1329
moderation_latency
(null)
generation_time
10060
tokens_prompt
77
tokens_completion
397
native_tokens_prompt
67
native_tokens_completion
375
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
0.000355395
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"0f7a5c32-f5fd-4f4d-bab8-cb81a687b204"
is_byok
false
latency
271
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-1777126851-b8kAG85PPUaGU6KASOsa"
session_id
(null)
api_type
"completions"
id
"gen-1777126851-uwWWrMDFdbAzKHpvD7hQ"
upstream_id
"0f7a5c32-f5fd-4f4d-bab8-cb81a687b204"
total_cost
0.000355395
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
239
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
245
wordsDialogue
245
18.3940%