NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5VY1ZNHT52020VSJD3A49
Run Details
Model:
DeepSeek V3.1
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
19.9s
Cost:
$0.000212
Provider:
SambaNova
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 adjusted her binoculars, scowling at the vibrant bouncy castle defiling the pristine lawn of the target's suburban fortress. "I hate clowns," she muttered. Next to her, Bill, a mountain of a man in an absurdly tight floral print shirt, scribbled furiously on a notepad. "The target is an eight-year-old female, heavily guarded by hyper-caffeinated parents. Primary acquisition is a pile of wrapped goods near the dessert table," he recited, tapping his pencil. Molly snatched the notepad. His 'blueprint' was a crude stick-figure drawing of a house with a giant arrow pointing to a circle labelled ‘loot’. "This is your plan? A drawing of a sad house?" Bill looked crestfallen. "It's a happy house! See the smile?" "Bill, this is a high-stakes operation! We need finesse. Distraction, infiltration, exfiltration." "I brought the distraction," he said proudly, producing a whoopee cushion from his pocket. Molly buried her face in her hands. "A party horn would have been a better choice." "The element of surprise is key," he insisted, solemnly placing the whoopee cushion back into his tactical fanny pack. Molly just sighed, already imagining the police report.
created_at
"2026-02-16T21:32:15.714692+00:00"
2/16/2026, 9:32:15 PM
model
"deepseek/deepseek-chat-v3.1"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1795
moderation_latency
(null)
generation_time
19927
tokens_prompt
95
tokens_completion
308
native_tokens_prompt
67
native_tokens_completion
269
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
0.0002118
router
(null)
provider_responses
0
id
"1c356aa1-ae11-4c99-a516-fdffa41c6683"
status
200
is_byok
false
latency
1795
endpoint_id
"1dda4bb9-c626-4816-bb54-99665323fef0"
provider_name
"SambaNova"
model_permaslug
"deepseek/deepseek-chat-v3.1"
api_type
"completions"
id
"gen-1771277514-QtFCt1BPP4KrRUG9pITx"
upstream_id
"1c356aa1-ae11-4c99-a516-fdffa41c6683"
total_cost
0.0002118
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SambaNova"
Evaluation details
Result
Evaluator
Details
Meta Data
93.6496%
Matches word count
n/a
neededClean
false
words
191
0.0000%
Dialogue to Total Word Ratio
Ratio: 51.31%, Deviation: 41.31%
neededClean
false
wordsTotal
191
wordsDialogue
98
46.8248%