NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5SRX4Q1B8YHM0QDMD6DBD
Run Details
Model:
DeepSeek V3 (2024-12-26)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
8.2s
Cost:
$0.000358
Provider:
Novita
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 the oversized clown nose while Bill struggled to tie his balloon animal into something resembling a dog. The van smelled like cheap face paint and regret. “This is the dumbest plan yet,” Bill muttered, twisting the green balloon into a questionable knot. Molly tossed him a rainbow wig. “Relax. No one suspects clowns. Especially not at a six-year-old’s birthday party.” Outside, the sounds of squealing children and off-key karaoke drifted through the cracked window. Molly checked the duffel bag—empty, save for a few stray candy wrappers. “We go in, distract with balloon animals, grab the presents, and vanish before the cake’s even cut.” Bill frowned. “What if someone notices?” “Then we do the one thing clowns do best.” She grinned. “Run away screaming.” A sudden burst of party horns made them both jump. Bill sighed and pulled the wig over his head. “I hate my life.” Molly slapped on a manic smile. “Break a leg. Or, you know, a piñata.” They stepped out into the chaos, their ridiculous disguises blending perfectly into the madness. The heist was on.
created_at
"2026-02-16T21:30:52.532505+00:00"
2/16/2026, 9:30:52 PM
model
"deepseek/deepseek-chat-v3"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
843
moderation_latency
(null)
generation_time
8167
tokens_prompt
77
tokens_completion
303
native_tokens_prompt
66
native_tokens_completion
255
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
0.0003579
router
(null)
provider_responses
0
id
"0bba65fb26f15e2bda012c3a64772afe"
status
200
is_byok
false
latency
843
endpoint_id
"cefb5a1e-9fea-4496-9a64-4e1b11a7cc8c"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-chat-v3"
api_type
"completions"
id
"gen-1771277444-hrEUviXcsQjYRXUfQYpY"
upstream_id
"0bba65fb26f15e2bda012c3a64772afe"
total_cost
0.0003579
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
51.9255%
Matches word count
n/a
neededClean
false
words
184
0.0000%
Dialogue to Total Word Ratio
Ratio: 35.33%, Deviation: 25.33%
neededClean
false
wordsTotal
184
wordsDialogue
65
25.9628%