NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM60BFSYDYRS2TAQQ5KC5N5
Run Details
Model:
DeepSeek V3 (2025-03-24)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
3.9s
Cost:
$0.000399
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
The party decorations fluttered in the breeze like neon evidence of their impending crime. Molly adjusted her oversized sunglasses—disguise number three this week—while Bill fiddled with a walkie-talkie that had seen better decades. "Think they’ve got cake?" Bill whispered, eyeing the bouncy castle like it was a vault. Molly sighed. "Focus. Presents first, diabetes later." They crouched behind a hedge shaped like a unicorn, its glittery mane scratching Bill’s nose. Inside, children shrieked with joy, oblivious to the duo plotting their giftpocalypse. Molly unrolled a blueprint on the grass—drawn in crayon, stolen from a kindergartener earlier. "Guards?" Bill asked, squinting. "Two. One’s got a juice box, the other’s napping in the ball pit." Bill nodded solemnly. "Weapons?" Molly held up a confetti cannon. "Distraction." A sudden squeal from the party made them freeze. A toddler wobbled toward the hedge, clutching a half-eaten cupcake. Molly and Bill held their breath. The kid stared, then toddled away, leaving frosting smeared on the unicorn’s hoof. "Close call," Bill muttered. Molly checked her watch. "Go time. Remember—no witnesses, no mercy, and for heaven’s sake, don’t trip on the piñata." Bill saluted. "Happy heisting." They crept forward, the scent of sugar and poor life choices hanging heavy in the air.
created_at
"2026-02-16T21:34:24.359472+00:00"
2/16/2026, 9:34:24 PM
model
"deepseek/deepseek-chat-v3-0324"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
412
moderation_latency
(null)
generation_time
3833
tokens_prompt
77
tokens_completion
369
native_tokens_prompt
69
native_tokens_completion
340
native_tokens_completion_images
0
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
0.00039943
router
(null)
provider_responses
0
id
"65f04afc29f3ea9fef49392e50ebff86"
status
200
is_byok
false
latency
412
endpoint_id
"3a816eb8-7a0b-4a9a-b497-e3a1efb349fc"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-chat-v3-0324"
api_type
"completions"
id
"gen-1771277659-hZ0wfaxxjk8bi24fNpZP"
upstream_id
"65f04afc29f3ea9fef49392e50ebff86"
total_cost
0.00039943
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
86.3803%
Matches word count
n/a
neededClean
false
words
211
19.2796%
Dialogue to Total Word Ratio
Ratio: 21.33%, Deviation: 11.33%
neededClean
false
wordsTotal
211
wordsDialogue
45
52.8300%