NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2E63E7MPT5SFCR9B59G7M0
Run Details
Model:
DeepSeek V4 Flash
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
4.9s
Cost:
$0.000087
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
86.38%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
43.1902%
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
The helium tank hissed like a punctured ego as Molly adjusted the nozzle on her inflatable unicorn costume. “Bill, the invite says ‘Uncle Larry’s Magical Menagerie.’ We’re the last act.” Bill, already stuffed into a bear suit that smelled faintly of regret and mothballs, grunted. “And the loot is in the bounce house. You sure?” Molly smirked, the unicorn horn wobbling. “I saw the mom tape the gift cards to the inflatable dolphin. They think hiding them in the prize pool is clever. We extract, pop the slide, and vanish.” Bill tugged at his bear head. “What if a kid wants a balloon animal?” Molly’s eyes gleamed. “You distract. I’ll raid the goody bags. Remember: no eye contact, no autographs, and for the love of glitter, don’t sneeze in the face paint.” Bill sighed, a sound like a deflating tuba. “And the giant Jenga tower?” Molly kicked a foam block. “That’s for the parents. We use it as a diversion. When it falls, everybody cries, and we walk out with a thousand dollars in birthday cash.” Bill nodded, his bear snout twitching. “Fine. But I’m not eating the cake.”
created_at
"2026-04-25T13:45:07.787Z"
4/25/2026, 1:45:07 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
541
moderation_latency
(null)
generation_time
4807
tokens_prompt
77
tokens_completion
289
native_tokens_prompt
67
native_tokens_completion
276
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
0.00008666
router
(null)
provider_responses
0
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"f80dd259-4ebf-43cc-aae5-71c056585780"
is_byok
false
latency
273
model_permaslug
"deepseek/deepseek-v4-flash-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-1777124707-LzClmSZqGMOV80gl9nqU"
session_id
(null)
api_type
"completions"
id
"gen-1777124707-qu99tfl19vUzNjBEeqKl"
upstream_id
"f80dd259-4ebf-43cc-aae5-71c056585780"
total_cost
0.00008666
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
86.38%
Matches word count
n/a
neededClean
false
words
189
0.00%
Dialogue to Total Word Ratio
Ratio: 64.55%, Deviation: 54.55%
neededClean
false
wordsTotal
189
wordsDialogue
122
43.1902%