NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5DHJHK72T8BZ47MM3QP6X
Run Details
Model:
DeepSeek V3.1
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
16.4s
Cost:
$0.000200
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
“It’s a kid’s birthday party, Bill. Not the royal mint.” “The principle is the same, Molly! Opportunity and execution. This is a soft target, but a fortress of unpredictability. Our biggest threat isn’t a guard, it’s a sugar-crazed seven-year-old.” “So what’s the plan?” “We go in as distant relatives. You create a distraction. I suggest a full-blown tantrum over the lack of gluten-free cake options.” “And then?” “While the parents are pacifying you, I’ll slip into the ‘gift room’—the walk-in closet under the stairs. I’ll pass the loot out the small window to our getaway driver.” “We have a getaway driver?” “My cousin Vinny. He’ll be waiting in the minivan, disguised as a soccer mom. We load the swag and we’re gone before they even cut the cake.” “Bill, this is the most ridiculous, over-complicated plan you’ve ever had.” “Is that a no?” “It’s a ‘what’s my cut?’ Do they have a piñata? I want first swing at the piñata.”
created_at
"2026-02-16T21:24:19.988225+00:00"
2/16/2026, 9:24:19 PM
model
"deepseek/deepseek-chat-v3.1"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
855
moderation_latency
(null)
generation_time
16341
tokens_prompt
95
tokens_completion
281
native_tokens_prompt
67
native_tokens_completion
253
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
0.0001998
router
(null)
provider_responses
0
id
"a609431e-336f-4fb8-9f78-3bf0e7562cc8"
status
200
is_byok
false
latency
853
endpoint_id
"1dda4bb9-c626-4816-bb54-99665323fef0"
provider_name
"SambaNova"
model_permaslug
"deepseek/deepseek-chat-v3.1"
api_type
"completions"
id
"gen-1771277043-x7ZuoJ53kQWJbv8h2osW"
upstream_id
"a609431e-336f-4fb8-9f78-3bf0e7562cc8"
total_cost
0.0001998
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SambaNova"
Evaluation details
Result
Evaluator
Details
Meta Data
0.0007%
Matches word count
n/a
neededClean
false
words
167
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
167
wordsDialogue
167
18.3943%