NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2F33K1W0VEGPHVK060TGN3
Run Details
Model:
DeepSeek V4 Pro
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
14.7s
Cost:
$0.000358
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 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
The warehouse smelled of damp cardboard and rust, their current planning stage existing entirely inside a decommissioned ice-cream truck. Molly tapped the park blueprints with a licorice stick. “The clown is the key variable, Bill. Is he a real clown or a gormless uncle in a rented tragedy suit?” Bill squinted through a party blower he was using as a telescope. “That’s profiling. Rent-a-Clown Gigglesmith could be a master safecracker for all we know. We treat him as hostile.” “Hostile giggles, check. Now, the bouncy castle. I enter as a stressed mother. I’ll have the correct emotional armour—smudged mascara, a gluten-free nut-free cupcake tower.” “And I’ll be the incompetent balloon man, a classic ruse. It’s a non-threatening entropy delivery system. I trip, I flail, a hundred helium balloons release, total aerial chaos.” “Perfect. Under the cover of floating SpongeBobs, I pop the piñata blind. I’m not pulling a string, Bill, I’m going in full-swing with a bedtime story about a visually impaired bat. The presents drop like ugly, wrapped fruit.” Bill nodded, tapping a crude map of the gift table. “The bag deployment must be synesthetic. I hit the button on my oversized clown flower, and it doesn’t squirt water, it squirts a plume of glitter. Choking, beautiful, daylight-smuggling glitter.” “We make the exit via the pony-ride circuit. We swap the loot into feedbags, and I whisper ‘gravy train’ to the lead pony. If anyone asks, we’re just two emotionally shattered parents chasing a terrified miniature horse. It’s tragic, not criminal.”
created_at
"2026-04-25T14:01:02.747Z"
4/25/2026, 2:01:02 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1143
moderation_latency
(null)
generation_time
10152
tokens_prompt
77
tokens_completion
416
native_tokens_prompt
67
native_tokens_completion
378
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
0.000358005
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"bede989a-441a-4740-96ed-2e33f63f7951"
is_byok
false
latency
285
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-1777125662-7vcZiZXSywHbgcuM5cKU"
session_id
(null)
api_type
"completions"
id
"gen-1777125662-ZtjsyuBcxmLF4ALQrnX4"
upstream_id
"bede989a-441a-4740-96ed-2e33f63f7951"
total_cost
0.000358005
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: 80.46%, Deviation: 30.46%
neededClean
false
wordsTotal
261
wordsDialogue
210
0.0000%