NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5W38QYPE66CJ9ACWW83KC
Run Details
Model:
DeepSeek V3.1
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
17.7s
Cost:
$0.000299
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 traced a chubby crayon line on the floorplan, her expression grim. "The target is heavily fortified." Bill peered over her shoulder, clutching a half-eaten jam sandwich he’d sourced from a nearby kitchen. The blueprint was, in fact, a child’s drawing of a house with a lopsided roof and a smiling sun in the corner. "The 'Dragon's Lair' is the main thoroughfare," Molly continued, pointing to a scribbled green monster labeled 'Fluffy.' "Intel suggests a territorial miniature schnauzer. Distract it." Bill swallowed a mouthful of bread. "With what?" "A higher-value offering. I’m thinking a squeaky chicken." She moved her finger to a room marked with a wobbly 'X'. "The vault. Full of high-end loot: plastic jewels, construction bricks, possibly a timed explosive device disguised as a 'Pop-Up Pirate' game." Bill nodded, wiping jam on his trousers. “Extraction?” “Standard procedure. Through the garden, over the fence. But the primary obstacle isn't security, it's morale." She fixed him with a stern look. "One of the tiny operatives might offer you a piece of cake. Under no circumstances accept. Mission focus is paramount.” Bill sighed, his shoulders slumping. The true cost of crime was steep.
created_at
"2026-02-16T21:32:18.335132+00:00"
2/16/2026, 9:32:18 PM
model
"deepseek/deepseek-chat-v3.1"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1930
moderation_latency
(null)
generation_time
17508
tokens_prompt
95
tokens_completion
318
native_tokens_prompt
70
native_tokens_completion
280
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
0.0002989
router
(null)
provider_responses
0
status
429
is_byok
false
latency
67
endpoint_id
"012f7d1f-23d4-4d03-9aa3-432d8ad82757"
provider_name
"DeepInfra"
model_permaslug
"deepseek/deepseek-chat-v3.1"
1
id
"019c685e12c4e712cbc866d116fb3731"
status
200
is_byok
false
latency
1930
endpoint_id
"5d5c9c1d-af0d-4e4a-8aee-c5cd2b3883f3"
provider_name
"SiliconFlow"
model_permaslug
"deepseek/deepseek-chat-v3.1"
api_type
"completions"
id
"gen-1771277520-Rmabj8Y3vBLZIvVIgYhb"
upstream_id
"019c685e12c4e712cbc866d116fb3731"
total_cost
0.0002989
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SiliconFlow"
Evaluation details
Result
Evaluator
Details
Meta Data
99.7443%
Matches word count
n/a
neededClean
false
words
196
0.0000%
Dialogue to Total Word Ratio
Ratio: 44.39%, Deviation: 34.39%
neededClean
false
wordsTotal
196
wordsDialogue
87
49.8722%