NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2H7ZTGSAT7KGABW2SGRRSQ
Run Details
Model:
DeepSeek V4 Pro
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
9.1s
Cost:
$0.000308
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
48.8138%
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 catering van smelled of synthetic cheese and bad decisions. Molly unfurled a glitter-encrusted blueprint across the crates of juice boxes, her finger tracing a corridor marked ‘Bouncy Castle’. “Alright,” Molly said, “the cake arrives at fourteen hundred hours. I’ll distract the clown. You’re on pinyata demolition.” “You distract the clown?” Bill said, recoiling. “Last time you ‘distracted’ a children’s entertainer, he required therapy and a tetanus shot.” “A sacrifice I was willing to make,” Molly said. “Focus. You’ll infiltrate via the ball pit. The haul is under the ‘Pin the Tail’ easel. Three tablets, a robotic dog, and a suspiciously heavy box labelled ‘Grandma’s Love’.” “I still say we just RSVP’d yes,” Bill said. “My casserole is legendary.” “We’re thieves, Bill, not potluck savants,” Molly said. “We arrive like wraiths, we leave like wraiths with wagonloads of loot. Now, the passphrase for the hired Cinderella is ‘The glass slipper is a safety hazard.’ She’ll hand over the master key to the gift table.” “And if a four-year-old breaks your alibi?” Bill asked. Molly snapped the blueprint shut, her eyes glinting like polished coal. “Then we weaponise the party bags. Nobody questions a sudden, tactical glitter bomb. It buys us a solid ninety seconds of weeping chaos.”
created_at
"2026-04-25T14:38:35.348Z"
4/25/2026, 2:38:35 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1460
moderation_latency
(null)
generation_time
9042
tokens_prompt
77
tokens_completion
362
native_tokens_prompt
67
native_tokens_completion
321
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
0.000308415
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"7fec3019-9e98-414e-b9be-952d80ca2828"
is_byok
false
latency
244
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-1777127915-7WuUSHBBt8EfsCcQhP6q"
session_id
(null)
api_type
"completions"
id
"gen-1777127915-8eyDBTm9RF3vhIUJe7DM"
upstream_id
"7fec3019-9e98-414e-b9be-952d80ca2828"
total_cost
0.000308415
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
97.63%
Matches word count
n/a
neededClean
false
words
207
0.00%
Dialogue to Total Word Ratio
Ratio: 75.24%, Deviation: 25.24%
neededClean
false
wordsTotal
210
wordsDialogue
158
48.8138%