NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-25-01KQ2FQ6VXPFNBFKFTKWWVM4V9
Run Details
Model:
DeepSeek V4 Pro (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 1s
Cost:
$0.002550
Provider:
DeepSeek
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
65.34%
Dialogue to Total Word Ratio
(details)
82.6615%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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 peered through binoculars. "The bouncy castle is at full inflation." "I still say we're overcomplicating this. Two words: piƱata diversion." "You want to blindfold a clown?" "I want to create a candy frenzy. Kids scramble, we grab the gift table, slip out dressed as party entertainers." "Our party entertainer outfits are yellow t-shirts that say 'Staff.' We'll look like escaped bananas." "Bananas are non-threatening. I'll do balloon animals to blend in." "You can only make a sick dachshund. A four-year-old said it looked like a sad intestine." "I've been workshopping a poodle. Okay, new plan: you distract parents with a juice-box pyramid scheme, I'll liberate the presents." "A juice-box pyramid scheme? You think they'll invest in bulk apple juice?" "Fine. We go in as premium face-painters. I do a tiger, you do a butterfly, we rob them blind." "I have a tremor from too much espresso. That kid will end up a haunted Picasso." "Think like them. What's the one thing a children's party needs more than gifts?" "A nap time enforcer?" "Exactly. We pose as sleep consultants. We swaddle the gifts and wheel them out in a stroller." "That's... actually not terrible. But you have to wear the bonnet." "Deal."
created_at
"2026-04-25T14:11:56.929Z"
4/25/2026, 2:11:56 PM
model
"deepseek/deepseek-v4-pro-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
851
moderation_latency
(null)
generation_time
60705
tokens_prompt
77
tokens_completion
2928
native_tokens_prompt
67
native_tokens_completion
2898
native_tokens_completion_images
(null)
native_tokens_reasoning
2606
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
0.002550405
router
(null)
provider_responses
0
endpoint_id
"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id
"2b751f8b-4074-4d96-bd1a-02282ae80547"
is_byok
false
latency
269
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-1777126316-qgamPhFCNnp0MVwr9J7V"
session_id
(null)
api_type
"completions"
id
"gen-1777126316-Nha9SXSXWDtnkPcS2e5b"
upstream_id
"2b751f8b-4074-4d96-bd1a-02282ae80547"
total_cost
0.002550405
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepSeek"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
202
65.34%
Dialogue to Total Word Ratio
Ratio: 98.08%, Deviation: 8.08%
neededClean
false
wordsTotal
208
wordsDialogue
204
82.6615%