NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5BQ5QRHF4F353XWKRSFXX
Run Details
Model:
DeepSeek V3.2
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
15.7s
Cost:
$0.000254
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 spread the crayon-drawn map across the weathered table. The target was a suburban bungalow, currently housing the seventh birthday party of one Timothy Perkins. Bill squinted at the crude diagram, his brow furrowed in concentration usually reserved for museum alarms, not a piñata. “Clown patrol here,” Molly whispered, tapping a sketch of a man with oversized shoes. Bill nodded, adjusting an imaginary tie. “Distraction plan?” Their operation was meticulous. Molly would enter via the garden slide during the cake frenzy, while Bill, disguised as a distant uncle, would disable the watchdog—a geriatric terrier named Mr. Wiggles. The loot, wrapped in shiny paper, would be extracted via a getaway wagon disguised as a recycling bin. Molly reviewed the inventory list: action figures, glitter art kits, a junior chemistry set. She imagined the chaos: sticky fingers, spilled juice, the deafening chorus of childish glee. It was the perfect cover. Bill practiced his “jolly relative” smile in a compact mirror; it looked more like a grimace. They shared a solemn, professional nod. This was their most audacious caper yet, a symphony of misdirection targeting the ultimate vault: a living room strewn with wrapping paper and innocent joy. The clock ticked toward zero hour.
created_at
"2026-02-16T21:23:19.597541+00:00"
2/16/2026, 9:23:19 PM
model
"deepseek/deepseek-v3.2-20251201"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2876
moderation_latency
(null)
generation_time
15564
tokens_prompt
77
tokens_completion
674
native_tokens_prompt
67
native_tokens_completion
562
native_tokens_completion_images
(null)
native_tokens_reasoning
291
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
0.00025413
router
(null)
provider_responses
0
id
"019c6855de583ea9cf0f2b188b393066"
status
200
is_byok
false
latency
2876
endpoint_id
"b39a588a-b338-43ba-b046-226b9e24afa8"
provider_name
"SiliconFlow"
model_permaslug
"deepseek/deepseek-v3.2-20251201"
api_type
"completions"
id
"gen-1771276983-mRs4QMns7jTxxXFISOLh"
upstream_id
"019c6855de583ea9cf0f2b188b393066"
total_cost
0.00025413
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
83.1723%
Dialogue to Total Word Ratio
Ratio: 3.45%, Deviation: 6.55%
neededClean
false
wordsTotal
203
wordsDialogue
7
91.5456%