NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5HP36HA421AQZFGNTES9B
Run Details
Model:
DeepSeek V3 (2025-03-24)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
8.1s
Cost:
$0.000316
Provider:
SiliconFlow
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 adjusted the fake mustache she’d glued to her upper lip and squinted at the handwritten invitation Bill had just handed her. The looping cursive declared *"You're Invited to Timmy's Super-Duper 6th Birthday Bash!"* in glitter-filled exuberance. Bill tapped the address scribbled at the bottom. "Easy in, easy out," he murmured, rolling up the sleeves of his borrowed clown costume—two sizes too small and smelling faintly of expired cotton candy. "Kids’ parties are chaos. Nobody pays attention." Molly grimaced as sweat trickled down her neck under the scratchy polyester suit. "What’s the plan if we run into a hyperactive six-year-old with a squirt gun?" "Distraction. I brought a piñata full of candy and loose change." He wiggled a bat ominously. "Kids love property destruction." She sighed. "We’re the worst people in the world." "Professional worst people," Bill corrected, adjusting his rainbow wig. "Now come on. If we wait much longer, all the good loot’ll be opened, and we’ll be stuck with action figures missing limbs." Molly nodded, shouldering a burlap sack labeled *"PARTY SUPPLIES."* The front door loomed ahead, balloons bobbing. Somewhere inside, a kazoo wheezed. They were ready.
created_at
"2026-02-16T21:26:27.462318+00:00"
2/16/2026, 9:26:27 PM
model
"deepseek/deepseek-chat-v3-0324"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2388
moderation_latency
(null)
generation_time
8051
tokens_prompt
77
tokens_completion
326
native_tokens_prompt
66
native_tokens_completion
299
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
0.0003155
router
(null)
provider_responses
0
id
"019c6858d950870f22d83b7746f62368"
status
200
is_byok
false
latency
2388
endpoint_id
"d562908f-c5eb-4a32-9a91-24d53b176fd8"
provider_name
"SiliconFlow"
model_permaslug
"deepseek/deepseek-chat-v3-0324"
api_type
"completions"
id
"gen-1771277178-WKB07tjX9sV55uKIRoYX"
upstream_id
"019c6858d950870f22d83b7746f62368"
total_cost
0.0003155
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SiliconFlow"
Evaluation details
Result
Evaluator
Details
Meta Data
98.7124%
Matches word count
n/a
neededClean
false
words
194
0.0000%
Dialogue to Total Word Ratio
Ratio: 44.33%, Deviation: 34.33%
neededClean
false
wordsTotal
194
wordsDialogue
86
49.3562%