NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5J995F305GMC6ZFJMR9AM
Run Details
Model:
DeepSeek V3 (2025-03-24)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
11.4s
Cost:
$0.000324
Provider:
SiliconFlow
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 fake mustache in the rearview mirror, frowning. "I still think the clown costume was overkill." Bill tightened his rainbow wig and sighed. "We blend in. That’s the genius of it. Nobody suspects clowns." "Everyone suspects clowns," Molly muttered. "Especially when they’re carrying a giant sack labeled ‘Loot.’" Bill glanced at the sack, then hastily turned it inside out. "Better?" "No. Now it just says ‘Toys’ in glitter. You’re *terrible* at this." "I’m improvisational. Besides, kids love glitter." Bill checked his watch. "Party’s in five. You got the distraction ready?" Molly held up a whoopee cushion and a smoke bomb. "Classics never fail." Bill grinned. "Perfect. You cause chaos, I grab the goods." "What’s my cut?" "Thirty percent." Molly scoffed. "Fifty. I’m the one risking my dignity with the whoopee cushion." "Fine," Bill grumbled. "But you’re also on cupcake duty." "Deal." They fist-bumped just as a patrol car rolled past. Both froze, then burst into exaggerated clown laughter until it turned the corner. Molly exhaled. "We are *so* going to jail." Bill adjusted his giant shoes. "Worth it."
created_at
"2026-02-16T21:26:50.681814+00:00"
2/16/2026, 9:26:50 PM
model
"deepseek/deepseek-chat-v3-0324"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3664
moderation_latency
(null)
generation_time
11394
tokens_prompt
77
tokens_completion
326
native_tokens_prompt
66
native_tokens_completion
307
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
0.0003235
router
(null)
provider_responses
0
id
"019c685925f86eadcd31e093bae10c18"
status
200
is_byok
false
latency
3664
endpoint_id
"d562908f-c5eb-4a32-9a91-24d53b176fd8"
provider_name
"SiliconFlow"
model_permaslug
"deepseek/deepseek-chat-v3-0324"
api_type
"completions"
id
"gen-1771277198-vnMzckydMI4BhOuWyt4l"
upstream_id
"019c685925f86eadcd31e093bae10c18"
total_cost
0.0003235
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SiliconFlow"
Evaluation details
Result
Evaluator
Details
Meta Data
27.1658%
Matches word count
n/a
neededClean
false
words
181
89.2926%
Dialogue to Total Word Ratio
Ratio: 55.80%, Deviation: 5.80%
neededClean
false
wordsTotal
181
wordsDialogue
101
58.2292%