NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5D6QMMQ68TG77YNMYZD5G
Run Details
Model:
DeepSeek V3 (2024-12-26)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
8.9s
Cost:
$0.000442
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 fake mustache clinging precariously to her upper lip while Bill squinted at the crudely drawn map of the backyard. The plan was simple: sneak in during the chaos of little Timmy’s birthday party, grab the presents, and vanish before anyone noticed the cake was missing too. “You sure this’ll work?” Bill whispered, eyeing the piñata suspiciously. It swung gently in the breeze, as if mocking them. Molly rolled her eyes. “It’s a party for six-year-olds, Bill. They’re more likely to rat us out for stealing the candy than calling the cops.” Bill frowned but nodded, stuffing a spare party hat into his pocket—just in case. They crouched behind a bush, watching as a herd of sugar-fueled children stampeded past the gift table. The presents, wrapped in obnoxiously bright paper, sat unattended. “Now?” Bill asked, fingers twitching. Molly sighed. “No, we wait for the magician. Distraction’s key.” Bill groaned. “I hate clowns.” “He’s a magician.” “Same difference.” The magician arrived in a puff of glitter, and the children shrieked with delight. Molly elbowed Bill. “Go time.” Bill hesitated. “What if we get caught?” Molly grinned. “We’ll say we’re the entertainment.” Bill looked at his stolen party hat. “We’re doomed.”
created_at
"2026-02-16T21:24:01.412242+00:00"
2/16/2026, 9:24:01 PM
model
"deepseek/deepseek-chat-v3"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
755
moderation_latency
(null)
generation_time
8816
tokens_prompt
77
tokens_completion
363
native_tokens_prompt
66
native_tokens_completion
320
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
0.0004424
router
(null)
provider_responses
0
id
"83f6a9c22d1b553f89df4a4d865d12f5"
status
200
is_byok
false
latency
755
endpoint_id
"cefb5a1e-9fea-4496-9a64-4e1b11a7cc8c"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-chat-v3"
api_type
"completions"
id
"gen-1771277032-smtwMPQ9lPEqsuwHXmKd"
upstream_id
"83f6a9c22d1b553f89df4a4d865d12f5"
total_cost
0.0004424
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
99.3769%
Matches word count
n/a
neededClean
false
words
205
0.0014%
Dialogue to Total Word Ratio
Ratio: 28.29%, Deviation: 18.29%
neededClean
false
wordsTotal
205
wordsDialogue
58
49.6892%