NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5DXZ1YGFNQ1CXE3DQD3XX
Run Details
Model:
DeepSeek V3.2
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
9.2s
Cost:
$0.000134
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
The air in the van was thick with cheap coffee and cheaper ambition. Molly peered through binoculars at the sprawling suburban backyard. “The target is fortified. Balloon moat. Bouncy castle drawbridge. A legion of sugar-fueled nine-year-olds.” Bill, studying a crayon map, nodded. “Our intel says the presents are consolidated at the foot of the Slide of Justice. The primary guard is a man in a soiled dinosaur costume answering to ‘Mr. Wiggles.’ His nap schedule is unpredictable.” Molly adjusted her headset. “We go in disguised as the missing clowns. You handle the diversion. I’ll bag the loot.” “My back’s still sore from the piñata extraction last month,” Bill grumbled, rubbing his shoulder. “That was a clean job. We got the candy and the novelty sunglasses.” “The birthday boy cried.” “Collateral damage,” Molly said, shrugging. “This is cleaner. In and out before the cake is served. The parents will be distracted by the impending frosting chaos.” Bill tested the extendable claw hidden in his sleeve. “And the exit strategy?” “The slip-n-slide to the neighbor’s hedge. The van will be idling behind the recycling bins.” “I don’t like it. It’s messy.” “It’s a birthday party, Bill. Everything’s messy.” She handed him a giant red nose. “Now, smile. You’re a professional.”
created_at
"2026-02-16T21:24:25.479228+00:00"
2/16/2026, 9:24:25 PM
model
"deepseek/deepseek-v3.2-20251201"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
977
moderation_latency
(null)
generation_time
9128
tokens_prompt
77
tokens_completion
367
native_tokens_prompt
67
native_tokens_completion
308
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
0.00013446
router
(null)
provider_responses
0
id
"c3c65a38fe2746fa838c574ba0063c92"
status
200
is_byok
false
latency
977
endpoint_id
"3570a950-b80f-4acd-bb92-8e1c1c51fafc"
provider_name
"AtlasCloud"
model_permaslug
"deepseek/deepseek-v3.2-20251201"
api_type
"completions"
id
"gen-1771277055-Sf58FDpn6ajAUZPpIlzH"
upstream_id
"c3c65a38fe2746fa838c574ba0063c92"
total_cost
0.00013446
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AtlasCloud"
Evaluation details
Result
Evaluator
Details
Meta Data
75.1556%
Matches word count
n/a
neededClean
false
words
213
0.0000%
Dialogue to Total Word Ratio
Ratio: 73.71%, Deviation: 63.71%
neededClean
false
wordsTotal
213
wordsDialogue
157
37.5778%