NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5S99X37YRY8XGRRJKW025
Run Details
Model:
DeepSeek V3 (2024-12-26)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
9.2s
Cost:
$0.000444
Provider:
Novita
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 fake mustache in the rearview mirror while Bill fiddled with a walkie-talkie. "You sure this is the right party?" he asked, squinting at a glittery invitation. "Positive," Molly said. "Little Timmy Wellington’s sixth birthday. Rich parents, spoiled kid—prime loot." Bill frowned. "There’s a clown." "So?" "I hate clowns." Molly rolled her eyes. "You’re a professional thief, Bill. Act like one." She shoved a pink balloon animal into his hands. "Here, blend in." Bill sighed. "Fine. But if that clown tries to hug me, I’m running." Molly checked her watch. "Okay, here’s the plan: you distract the parents with your ‘magic tricks’—" "Which I don’t know." "—while I load the presents into the piñata-shaped getaway car." Bill blinked. "We have a piñata-shaped getaway car?" "Surprise." Molly grinned. "Now, remember: if things go south, scream ‘Pin the tail on the donkey!’ and we bail." Bill nodded, then paused. "Wait, how do we carry all the presents?" Molly held up a giant sack labeled ‘SANTA’S SECRET STASH.’ Bill groaned. "We’re gonna die." "Only if you keep whining." Molly adjusted her mustache again. "Let’s go steal some Legos."
created_at
"2026-02-16T21:30:38.086806+00:00"
2/16/2026, 9:30:38 PM
model
"deepseek/deepseek-chat-v3"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
879
moderation_latency
(null)
generation_time
9184
tokens_prompt
77
tokens_completion
338
native_tokens_prompt
66
native_tokens_completion
321
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
0.0004437
router
(null)
provider_responses
0
id
"61e54de98d8a0ec3b3ae6b4856e7951f"
status
200
is_byok
false
latency
879
endpoint_id
"cefb5a1e-9fea-4496-9a64-4e1b11a7cc8c"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-chat-v3"
api_type
"completions"
id
"gen-1771277428-esdnBPWgqTj3Qy3mSzJ1"
upstream_id
"61e54de98d8a0ec3b3ae6b4856e7951f"
total_cost
0.0004437
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
95.9868%
Matches word count
n/a
neededClean
false
words
192
54.0859%
Dialogue to Total Word Ratio
Ratio: 58.85%, Deviation: 8.85%
neededClean
false
wordsTotal
192
wordsDialogue
113
75.0363%