NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2G1QNDJBGAW58MXJA1GVER
Run Details
Model:
DeepSeek V4 Flash (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
5.7s
Cost:
$0.000112
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
81.27%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
40.6364%
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
“Bill, you’re telling me we’re casing a bouncy castle?” Molly adjusted her ski mask, which looked absurd over her reading glasses. “It’s not just a castle. It’s the Bouncy Kingdom of Little Timmy’s fifth birthday. Inside that inflatable fortress are three dozen gift bags, each lined with premium chocolate and tiny action figures. We hit the gift table when the magician does the rabbit trick.” Bill squinted at the backyard. “The magician’s named Señor Wiggles. He has a parrot that squawks ‘Abracadabra.’ How do we even get past the parents?” “Easy. We pose as the entertainment. You’re Uncle Bob, the balloon animal guy. I’m your assistant, Glitter Glenda.” “Glitter Glenda? That sounds like a stripper name for toddlers.” “Focus, Bill. While you distract them with a horrifying giraffe balloon, I swap the presents with decoy bags filled with socks.” “Socks? They’ll riot.” “They’ll cry. Then eat cake. By the time they notice, we’ll be in the van with three dozen chocolate bars and a dozen glow-in-the-dark ninjas.” Bill sighed. “Fine. But I’m not doing a giraffe. I’m doing a sword.” “You are a grown man. Do the giraffe.”
created_at
"2026-04-25T14:17:41.81Z"
4/25/2026, 2:17:41 PM
model
"deepseek/deepseek-v4-flash-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
552
moderation_latency
(null)
generation_time
5603
tokens_prompt
77
tokens_completion
384
native_tokens_prompt
67
native_tokens_completion
366
native_tokens_completion_images
(null)
native_tokens_reasoning
72
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
0.00011186
router
(null)
provider_responses
0
endpoint_id
"722e0746-2034-4d6e-a08f-e6271849ee9e"
id
"05c81831-662e-4ae2-90de-68cf52151f05"
is_byok
false
latency
316
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-1777126661-gNa29XXdnJhOnQ2EdPEv"
session_id
(null)
api_type
"completions"
id
"gen-1777126661-aJ1muAZjL0zfrDRk4UCY"
upstream_id
"05c81831-662e-4ae2-90de-68cf52151f05"
total_cost
0.00011186
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
81.27%
Matches word count
n/a
neededClean
false
words
188
0.00%
Dialogue to Total Word Ratio
Ratio: 90.05%, Deviation: 40.05%
neededClean
false
wordsTotal
191
wordsDialogue
172
40.6364%