NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5J03T97VDF88F5A1Z8JXT
Run Details
Model:
DeepSeek V3.1
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
20.1s
Cost:
$0.000231
Provider:
SambaNova
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
The dusty beam of a single worklight illuminated a stack of crumpled blueprints. Molly tapped a heavily-inked schematic of a suburban bungalow. “The mark is a six-year-old named Timmy. His party is tomorrow. Maximum occupancy: thirty sugar-hyped minors and at least one overwhelmed parent.” Bill squinted at the drawing. “Defenses?” “Balloon-animal moat, a sole sentry dressed as a clown—call him ‘Jingles’—and a perimeter littered with those tiny, plastic dinosaurs that go straight to the arch of your foot. The real prize is in the living room, right next to the half-eaten sheet cake.” “Extraction point?” “We go in disguised as the hired entertainment. You’ll be ‘Professor Poppinflop,’ the world’s worst magician.” “And you?” Bill asked, dubious. “I’m your disgruntled assistant, ‘Mesmerella.’ While you’re ‘accidentally’ setting your own pants on fire during the disappearing rabbit trick, I’ll be loading the swag into your oversized prop suitcase.” Molly grinned. “We hit the loot piñata, nobody gets hurt, and we’re out before the clown finishes his first balloon poodle.” Bill sighed, rubbing his temples. “The things I do for a decent score. Just promise me there’s no actual face-painting involved.”
created_at
"2026-02-16T21:26:49.907888+00:00"
2/16/2026, 9:26:49 PM
model
"deepseek/deepseek-chat-v3.1"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
901
moderation_latency
(null)
generation_time
20072
tokens_prompt
95
tokens_completion
343
native_tokens_prompt
67
native_tokens_completion
294
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
0.00023055
router
(null)
provider_responses
0
id
"acdf8e05-23e9-421a-8255-5a8c4c350a45"
status
200
is_byok
false
latency
901
endpoint_id
"1dda4bb9-c626-4816-bb54-99665323fef0"
provider_name
"SambaNova"
model_permaslug
"deepseek/deepseek-chat-v3.1"
api_type
"completions"
id
"gen-1771277189-HEwVwplsAYMRovqEZu7N"
upstream_id
"acdf8e05-23e9-421a-8255-5a8c4c350a45"
total_cost
0.00023055
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SambaNova"
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: 80.41%, Deviation: 30.41%
neededClean
false
wordsTotal
194
wordsDialogue
156
49.3562%