NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5R3WY33RKH667J3ERDHAV
Run Details
Model:
DeepSeek V3.2
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
10.9s
Cost:
$0.000141
Provider:
AtlasCloud
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
Molly squinted at the childish map, a crude drawing of a suburban backyard dubbed “The Compound.” Bill, beside her in their stolen panel van, adjusted his black ski mask despite the summer heat. "The 'Loot Depot' is here, by the bouncy castle," she muttered, tapping a crayoned 'X'. The plan was simple, but fraught with unseen variables. The primary obstacle, besides a legion of sugar-fueled seven-year-olds, was "The Beast"—a drooling, easily bribed Saint Bernard named Butterscotch. Their entry point was the side gate, conveniently left ajar by arriving pizza delivery. Bill’s job was to create a diversion involving three whoopee cushions and a confetti cannon repurposed from a retirement home heist. Molly, smaller and quicker, would sweep the gift table, piling booty into a sack disguised as a piñata. Bill shifted nervously. "The noise… it’s a tactical risk." Molly didn’t look up. "It’s a birthday party, Bill. They’ll just think it’s part of the act." She finally stowed the map, her expression grave. "Remember, we’re in and out in ninety seconds. Maximum stealth. We avoid the clown at all costs. I don't trust his painted smile." They shared a tense nod. To an outsider, it was a ridiculous mission. To them, it was just another score, albeit one that likely contained more Lego sets than diamonds. The van door slid open with a quiet sigh. Showtime.
created_at
"2026-02-16T21:30:01.276699+00:00"
2/16/2026, 9:30:01 PM
model
"deepseek/deepseek-v3.2-20251201"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1210
moderation_latency
(null)
generation_time
10844
tokens_prompt
77
tokens_completion
358
native_tokens_prompt
67
native_tokens_completion
325
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)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.00014092
router
(null)
provider_responses
0
id
"ece97e55fb1a4f65ae656a193f1b566b"
status
200
is_byok
false
latency
1210
endpoint_id
"3570a950-b80f-4acd-bb92-8e1c1c51fafc"
provider_name
"AtlasCloud"
model_permaslug
"deepseek/deepseek-v3.2-20251201"
api_type
"completions"
id
"gen-1771277389-Y6wT5xge6D2wpOA23z5j"
upstream_id
"ece97e55fb1a4f65ae656a193f1b566b"
total_cost
0.00014092
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AtlasCloud"
Evaluation details
Result
Evaluator
Details
Meta Data
0.0304%
Matches word count
n/a
neededClean
false
words
230
1.4439%
Dialogue to Total Word Ratio
Ratio: 24.35%, Deviation: 14.35%
neededClean
false
wordsTotal
230
wordsDialogue
56
0.7371%