NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5GFG0YEKBRR3WTDN49J6Y
Run Details
Model:
DeepSeek V3.1
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
23.5s
Cost:
$0.000239
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 I’ve blueprinted the target," Molly said, spreading a crayon-drawn map on the table. “It’s a fortified playpen at the McAllister residence. High chair sentry at four o’clock.” Bill squinted. “Is that a chocolate pudding moat?” “Affirmative. But our window is small. The asset transfer happens during 'Happy Birthday'. The guests are distracted, singing the ritual song. That’s our in.” “Guards?” “One tall, skinny one they call 'Uncle Dan'. He’ll be manning the grill. Easily neutralized with a bad dad joke. The primary security is a six-year-old named Timmy. Hyper-vigilant. Loves his new toy fire truck. He will not let it out of his sight.” “So we separate him from the truck?” “No. We steal the truck. He’ll follow the asset, leading him right into our diversion: a rogue piñata. We grab the loot from the gift table during the ensuing sugar-fueled chaos.” Bill nodded grimly. “The perfect crime. What’s the exit strategy?” “Standard birthday party protocol. We blend into the fleeing parents. They call it ‘the witching hour’. Nobody questions a screaming adult with a stuffed goody bag.” “I love it. This is our biggest job yet.” “The biggest. Operation: Tiny Tim’s Loot is a go.”
created_at
"2026-02-16T21:26:03.770338+00:00"
2/16/2026, 9:26:03 PM
model
"deepseek/deepseek-chat-v3.1"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1788
moderation_latency
(null)
generation_time
23412
tokens_prompt
95
tokens_completion
342
native_tokens_prompt
67
native_tokens_completion
305
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
0.0002388
router
(null)
provider_responses
0
id
"a4883f9e-0148-49b5-b554-ceb8dce8f9bd"
status
200
is_byok
false
latency
1787
endpoint_id
"1dda4bb9-c626-4816-bb54-99665323fef0"
provider_name
"SambaNova"
model_permaslug
"deepseek/deepseek-chat-v3.1"
api_type
"completions"
id
"gen-1771277139-s9SxjSOWD2ouKJOTkiyE"
upstream_id
"a4883f9e-0148-49b5-b554-ceb8dce8f9bd"
total_cost
0.0002388
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SambaNova"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9190%
Matches word count
n/a
neededClean
false
words
203
99.5364%
Dialogue to Total Word Ratio
Ratio: 92.61%, Deviation: 2.61%
neededClean
false
wordsTotal
203
wordsDialogue
188
99.7277%