NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM612ZNPEEW2RS02HR6YY0W
Run Details
Model:
DeepSeek V3 (2025-03-24)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
7.7s
Cost:
$0.000315
Provider:
AtlasCloud
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 adjusted her oversized clown nose and frowned. “Bill, you sure this disguise will work?” Bill tightened the rainbow wig perched on his head. “Relax, Molls. No one suspects clowns. Especially not at a kid’s birthday party.” “Right, because clowns aren’t terrifying at all.” Molly rolled her eyes. “You realize we’re basically monsters, stealing from a bunch of five-year-olds?” “Nah, we’re doing ‘em a favor.” Bill shrugged. “Kids today have too many toys. We’re just… redistributing the wealth.” Molly snorted. “Wow. Justifying petty theft with social commentary. Classy.” “Stick to the plan: distract ‘em with magic tricks, swipe the presents while they’re cake-drunk, and boom—retirement fund.” “Magic tricks? You don’t know any.” “I can make a napkin disappear!” Bill demonstrated, promptly dropping it on the floor. Molly facepalmed. “We’re doomed.” “Trust me, Molls. By the time they realize the presents are gone, we’ll be halfway to Vegas.” She sighed. “Fine. But if we get caught, I’m blaming the clown thing.” Bill grinned. “Deal. Now, ready to go ruin some childhoods?” Molly adjusted her oversized shoes. “Ugh. Remind me why I partner with you again?” “Because no one else puts up with your nonsense.” “Fair.” She smirked. “Let’s go rob a birthday party.”
created_at
"2026-02-16T21:34:51.873444+00:00"
2/16/2026, 9:34:51 PM
model
"deepseek/deepseek-chat-v3-0324"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
826
moderation_latency
(null)
generation_time
7657
tokens_prompt
77
tokens_completion
388
native_tokens_prompt
67
native_tokens_completion
342
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
0.000315324
router
(null)
provider_responses
0
id
"76dfb3b30c6a42d2a3e87e2e916e444a"
status
200
is_byok
false
latency
826
endpoint_id
"5bb598f5-fd97-4f8b-91e4-ceab3743a03b"
provider_name
"AtlasCloud"
model_permaslug
"deepseek/deepseek-chat-v3-0324"
api_type
"completions"
id
"gen-1771277683-sF24Sv5dBCzHVx554H9K"
upstream_id
"76dfb3b30c6a42d2a3e87e2e916e444a"
total_cost
0.000315324
cache_discount
1.08e-7
upstream_inference_cost
0
provider_name
"AtlasCloud"
Evaluation details
Result
Evaluator
Details
Meta Data
98.7124%
Matches word count
n/a
neededClean
false
words
206
0.0000%
Dialogue to Total Word Ratio
Ratio: 77.67%, Deviation: 27.67%
neededClean
false
wordsTotal
206
wordsDialogue
160
49.3562%