NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5DFXJVGXS4017RBJH3AS4
Run Details
Model:
DeepSeek V3 (2025-03-24)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1.7s
Cost:
$0.000387
Provider:
Novita
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 party decorations flapped in the breeze like neon crime scene tape, taunting Molly and Bill from across the street. Molly adjusted her oversized sunglasses—disguised as a concerned aunt—while Bill nervously fiddled with a balloon animal he’d swiped from a vendor. “You sure this is the right house?” Bill whispered, eyeing the bouncy castle with suspicion. Molly rolled her eyes. “Yes. Rich kids, dumb parents. Perfect score.” They’d cased the joint for weeks—well, Molly had. Bill mostly ate cake samples. The plan was simple: blend in, grab the loot, vanish before the piñata broke. Bill squinted at the invitation in his hand. “It says ‘No Shoes, No Shirt, No Problem.’ What if they mean it?” Molly sighed. “Just act natural.” Bill stuffed the balloon giraffe into his pocket. “What’s natural at a kid’s party?” “Chaos.” Molly smirked, adjusting her sunhat. “And we’re professionals.” Inside, a toddler screamed bloody murder over a stolen juice box. Perfect cover. They exchanged a nod and strolled toward the gift table, where shiny boxes promised untold riches—or at least a decent pawn shop haul. Bill reached for a present. “Wait,” Molly hissed. “That one’s got a bow.” Bill froze. “So?” “So bows mean explosives.” Bill paled. “Since when?” Molly grinned. “Since I said so.”
created_at
"2026-02-16T21:24:03.62499+00:00"
2/16/2026, 9:24:03 PM
model
"deepseek/deepseek-chat-v3-0324"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
226
moderation_latency
(null)
generation_time
1531
tokens_prompt
77
tokens_completion
383
native_tokens_prompt
69
native_tokens_completion
329
native_tokens_completion_images
0
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)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.00038711
router
(null)
provider_responses
0
id
"cf9eadaa8b77cd918ab2d13ff4cde239"
status
200
is_byok
false
latency
226
endpoint_id
"3a816eb8-7a0b-4a9a-b497-e3a1efb349fc"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-chat-v3-0324"
api_type
"completions"
id
"gen-1771277041-nh1nnjh0sFt36kvrTSVg"
upstream_id
"cf9eadaa8b77cd918ab2d13ff4cde239"
total_cost
0.00038711
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
75.1556%
Matches word count
n/a
neededClean
false
words
213
0.0374%
Dialogue to Total Word Ratio
Ratio: 26.76%, Deviation: 16.76%
neededClean
false
wordsTotal
213
wordsDialogue
57
37.5965%