NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5DJY6TDZ1BMS32FW3QRYK
Run Details
Model:
DeepSeek V3.1
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
21.8s
Cost:
$0.000339
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 traced a chubby crayon line on the map. "The objective is the ‘Present Pile.’ Located under the giant inflatable rubber duck." Bill adjusted his fake mustache. "Security?" he whispered, leaning in. "Tight. A six-year-old named Timmy patrols the perimeter with a sticky lollipop. He suspects everyone." Molly pointed a pudgy finger. "Our primary obstacle is ‘The Gauntlet’." Bill peered at the diagram of a bouncy castle. "We go under cover of ‘Musical Chairs.’ The chaos will be deafening." "Precisely. You create a diversion. Trigger the bubble machine." "The old bubble-machine gambit. Classic." Bill chewed his lip. "Extraction?" "Once the loot is secured, we exfiltrate via the slip-n-slide. Mrs. Henderson will be distracted by the punchbowl." "Roger that." Bill’s stomach growled. "What about the cake?" "The cake is not the mission, Bill." "It’s a German chocolate, Molls. That’s a high-value target." "We’re professionals, Bill! Stick to the plan. Get in, grab the Paw Patrol loot, get out." She eyed him. "And don’t even think about the piñata." "The piñata’s a liability anyway," Bill sighed, "Too much noise." He looked at the map one last time, a glint in his eye. "Okay. Operation Sugar Rush is a go."
created_at
"2026-02-16T21:24:27.296227+00:00"
2/16/2026, 9:24:27 PM
model
"deepseek/deepseek-chat-v3.1"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1515
moderation_latency
(null)
generation_time
21808
tokens_prompt
95
tokens_completion
335
native_tokens_prompt
70
native_tokens_completion
320
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
0.0003389
router
(null)
provider_responses
0
id
"019c6856cf514814dacae0d542f6a7be"
status
200
is_byok
false
latency
1489
endpoint_id
"5d5c9c1d-af0d-4e4a-8aee-c5cd2b3883f3"
provider_name
"SiliconFlow"
model_permaslug
"deepseek/deepseek-chat-v3.1"
api_type
"completions"
id
"gen-1771277044-GBiBrtMGVL0Rh56afQ08"
upstream_id
"019c6856cf514814dacae0d542f6a7be"
total_cost
0.0003389
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SiliconFlow"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9190%
Matches word count
n/a
neededClean
false
words
203
0.0000%
Dialogue to Total Word Ratio
Ratio: 71.92%, Deviation: 21.92%
neededClean
false
wordsTotal
203
wordsDialogue
146
49.9595%