NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2DFH0XDMKSXVEH1CWQ3KB9
Run Details
Model:
DeepSeek V4 Pro
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
10.1s
Cost:
$0.000281
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
1.35%
Dialogue to Total Word Ratio
(details)
50.6765%
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 blew a rogue strand of hair from her eyes and tapped a crayon-drawn map against the laminate surface of a tiny school desk, her knees jutting up comically on either side. The hand-drawn floor plan featured a crude, wobbly X over a gift table guarded by what looked like a furious, spiked potato. Bill squinted, his borrowed elf costume groaning at the seams as he leaned in. “That’s the cake,” Molly whispered, her voice laced with deadly seriousness. “Billy the Butcher blockaded the goods with a three-tiered fondant fortress.” A distant shriek of glee from the soft-play jungle confirmed their window was closing. Bill cracked his knuckles, a gesture undermined by the jingle of brass bells on his curled felt shoes. “So I waddle in, jingle-jangle, cause a choc-ice diversion?” he murmured. A professional gleam lit Molly’s eyes as she unfolded a square of industrial-strength wrapping paper. “You’re the new hire, clumsy and festive. Trip, knock over the pinata, and while the sugar-crazed mob descends,” she paused, patting a tactical black sack lined with conductive fibres to defeat the squeaky toys, “Granny Glitterfingers here sweeps the treasure.” A slow grin spread across Bill’s face, appreciating the ballet of it all.
created_at
"2026-04-25T13:32:48.156Z"
4/25/2026, 1:32:48 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1025
moderation_latency
(null)
generation_time
9782
tokens_prompt
77
tokens_completion
320
native_tokens_prompt
67
native_tokens_completion
289
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
0.000280575
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"0e21e44f-4c4e-4adf-92b5-cd724037d74e"
is_byok
false
latency
274
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-1777123968-rL2OB9q9IGLcrY4CjuNO"
session_id
(null)
api_type
"completions"
id
"gen-1777123968-cgQQnKAm9K5lfdlq4ZC8"
upstream_id
"0e21e44f-4c4e-4adf-92b5-cd724037d74e"
total_cost
0.000280575
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
201
1.35%
Dialogue to Total Word Ratio
Ratio: 24.40%, Deviation: 14.40%
neededClean
false
wordsTotal
209
wordsDialogue
51
50.6765%