NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KC9H5PFE9YMPEEV0BXEF8S
Run Details
Model:
DeepSeek V4 Pro 0813 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
37.7s
Cost:
$0.009059
Provider:
Cloudflare
Evaluation summary
Score
Evaluator
Details Link
43.38%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
40.0831%
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
"We're not just waltzing into a bouncy castle heist, Bill. This is a toddler's birthday. Maximum security: one hired fairy, two grandparents asleep on a sofa." "So I bring the bolt cutters for the gift table?" "No, you bring a juice box and pretend you're lost. I'll be the clown." "You hate clowns." "I hate prison more. Now, the presents are piled by the chocolate fountain. We need a distraction." "I could sing 'Happy Birthday' in the wrong key." "The children would riot. We need subtle. You spill juice on the magician." "He's only doing balloon animals." "Even better. Wet balloon poodle. Chaos. While he's wiping his waistcoat, I grab the big one with the dinosaur wrapping paper." "How do you know it's big?" "I shook it at the gift table recon. Sounds like a toy cash register. We'll be rich." "Rich in plastic coins." "They're collectible. Now, what's your exit strategy?" "I crawl through the ball pit and out the back." "Brilliant. No one follows a grown man through forty thousand plastic balls." "Because they'll be too busy laughing." "Exactly. Let's move."
created_at
"2026-09-03T10:16:06.603Z"
9/3/2026, 10:16:06 AM
model
"deepseek/deepseek-v4-pro-20260813"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1738
moderation_latency
(null)
generation_time
37588
tokens_prompt
75
tokens_completion
2292
native_tokens_prompt
146
native_tokens_completion
2239
native_tokens_completion_images
(null)
native_tokens_reasoning
2011
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"
service_tier
(null)
usage
0.00905916
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788430566-hE08lFGwaC4QDVjF08XM"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788430566-ZPzY1f6QgkjQ340RsDw2"
upstream_id
"id-1788430568341"
provider_responses
0
endpoint_id
"b27d93a2-5f9d-4768-a1e0-a7b13ab9aaed"
id
"id-1788430568341"
is_byok
false
latency
1729
model_permaslug
"deepseek/deepseek-v4-pro-20260813"
provider_name
"Cloudflare"
status
200
total_cost
0.00905916
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Cloudflare"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
43.38%
Matches word count
n/a
neededClean
false
words
183
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
183
wordsDialogue
183
40.0831%