NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5FBH0QCZ5FNTJNRENWXHD
Run Details
Model:
DeepSeek V3 (2024-12-26)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
12.6s
Cost:
$0.000314
Provider:
DeepInfra
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
The room was dimly lit, the air thick with the scent of stale coffee and desperation. Molly leaned over a crumpled map of the neighborhood, her fingers tracing the route to the Thompson residence. Bill sat across from her, nervously twisting a rubber band around his fingers. A half-eaten donut lay forgotten on the table. Molly pointed to a circled address. "The party’s at two. Kids’ll be distracted by cake and clowns. Perfect chaos." Bill frowned, his brow furrowing like a crumpled napkin. "Clowns? I didn’t sign up for clowns. Clowns are creepy." "You’re thinking of mimes," Molly said, rolling her eyes. "Clowns are just sad people in makeup. Focus." Bill sighed, snapping the rubber band against his wrist. "Fine. But if one of them honks at me, I’m out." Molly smirked, tapping the map. "We go in through the backyard. Grab the presents, stash them in the laundry basket, and walk out like we’re the cleaning crew. Easy." Bill glanced at the calendar on the wall, counting the days until Christmas. "What if someone notices?" "They’ll be too busy wondering why their kid got socks instead of a gaming console," Molly replied, folding the map with a flourish. Bill nodded slowly, though his hands still trembled. "Alright. But you’re dealing with the clowns." "Deal," Molly said, tossing him a fake mustache. "Now, let’s get this show on the road."
created_at
"2026-02-16T21:25:15.623781+00:00"
2/16/2026, 9:25:15 PM
model
"deepseek/deepseek-chat-v3"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
244
moderation_latency
(null)
generation_time
12516
tokens_prompt
77
tokens_completion
362
native_tokens_prompt
66
native_tokens_completion
329
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
0.00031393
router
(null)
provider_responses
0
id
"chatcmpl-R9ornX9BYapQ0qG1STX2bdtG"
status
200
is_byok
false
latency
67
endpoint_id
"5294d55f-9012-496b-8f22-8cc919432dcd"
provider_name
"DeepInfra"
model_permaslug
"deepseek/deepseek-chat-v3"
api_type
"completions"
id
"gen-1771277102-5ZTAcUkXI19TgBzTQDqy"
upstream_id
"chatcmpl-R9ornX9BYapQ0qG1STX2bdtG"
total_cost
0.00031393
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
0.0098%
Matches word count
n/a
neededClean
false
words
231
0.0000%
Dialogue to Total Word Ratio
Ratio: 45.45%, Deviation: 35.45%
neededClean
false
wordsTotal
231
wordsDialogue
105
0.0049%