NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5VW9HB4JNMNMV3ZZFTBQ7
Run Details
Model:
DeepSeek V3.1
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
19.5s
Cost:
$0.000221
Provider:
SambaNova
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
“Okay, so the mark is a seven-year-old named Timmy,” Molly said, unfolding a crayon-drawn map. Bill squinted. “You got the intel from his little sister, didn’t you?” “She traded for a juice box. Focus. The objective is in the backyard. Peak vulnerability is during the magician’s final act, right after the pinata but before the cake meltdown.” “Security?” Bill asked, rubbing his chin. “Heavy. Two ‘Tiger Moms,’ a sleep-deprived dad on coffee duty, and a golden retriever named ‘Sparkles’ with a known weakness for dropped cocktail wieners.” “Our entrance?” “We pose as the inflatable castle delivery team. Our exit is the same. We load the loot into the giant bounce house bag.” Bill stared at the map. “The sheer audacity. It’s beautiful.” “High risk, high reward. We’re talking top-tier Lego sets, Bill. The good kind with the little wrench. We’ll be in and out before anyone notices the presents are gone.” “And if we’re made?” Molly grinned, holding up a small, brightly wrapped box. “We give them this.” “A diversion?” “A whoopee cushion. They’ll be laughing too hard to call the cops.”
created_at
"2026-02-16T21:32:12.789391+00:00"
2/16/2026, 9:32:12 PM
model
"deepseek/deepseek-chat-v3.1"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1455
moderation_latency
(null)
generation_time
19452
tokens_prompt
95
tokens_completion
322
native_tokens_prompt
67
native_tokens_completion
281
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
0.0002208
router
(null)
provider_responses
0
id
"c3643bde-a145-49d0-8f9d-f475ad1596aa"
status
200
is_byok
false
latency
1454
endpoint_id
"1dda4bb9-c626-4816-bb54-99665323fef0"
provider_name
"SambaNova"
model_permaslug
"deepseek/deepseek-chat-v3.1"
api_type
"completions"
id
"gen-1771277513-qQJdfK5rFerDNc27A3Oe"
upstream_id
"c3643bde-a145-49d0-8f9d-f475ad1596aa"
total_cost
0.0002208
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SambaNova"
Evaluation details
Result
Evaluator
Details
Meta Data
75.1556%
Matches word count
n/a
neededClean
false
words
187
94.0660%
Dialogue to Total Word Ratio
Ratio: 85.03%, Deviation: 4.97%
neededClean
false
wordsTotal
187
wordsDialogue
159
84.6108%