NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5G278FX70EB0XYCJ2115R
Run Details
Model:
DeepSeek V3 (2025-03-24)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
8.8s
Cost:
$0.000327
Provider:
AtlasCloud
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
“Alright, Molly, here’s the plan,” Bill whispered, crouching behind a bouncy castle. “We strike when they’re all distracted by the clown.” Molly frowned. “The clown’s juggling fire, Bill. What if he burns the place down before we get the loot?” “Even better—chaos is our getaway driver.” Bill adjusted his fake mustache. “You’ll pose as the pizza delivery guy.” “I’m wearing a tutu.” “Right. Plan B: you’re the ballet instructor.” “The kid’s six. They don’t *have* ballet instructors.” Bill sighed. “Fine. We improvise. You distract the parents with a fake allergy—say little Timmy’s allergic to happiness.” Molly rolled her eyes. “And what’re you doing?” “Professional present thief. I’ve got a sack and everything.” He held up a pillowcase. “That’s a Spider-Man pillowcase.” “It’s thematic.” A kid walked by, staring. Bill froze. “...Hide me.” Molly grabbed his head and shoved it into the ball pit. “We’re doomed.” Bill’s muffled voice came through. “Nonsense. This is genius.” “Your genius is currently drowning in plastic balls.” “Worth it.” He emerged, spitting out a blue one. “Let’s just grab the presents and run.” Molly groaned. “Fine. But if we get tackled by a dad in cargo shorts, I’m blaming you.” “Deal.” Bill grinned. “Happy heisting.”
created_at
"2026-02-16T21:25:35.128959+00:00"
2/16/2026, 9:25:35 PM
model
"deepseek/deepseek-chat-v3-0324"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
933
moderation_latency
(null)
generation_time
8731
tokens_prompt
77
tokens_completion
399
native_tokens_prompt
67
native_tokens_completion
355
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
0.000326764
router
(null)
provider_responses
0
id
"77f95e9a61c349ceb1bb05ab94ec46b6"
status
200
is_byok
false
latency
933
endpoint_id
"5bb598f5-fd97-4f8b-91e4-ceab3743a03b"
provider_name
"AtlasCloud"
model_permaslug
"deepseek/deepseek-chat-v3-0324"
api_type
"completions"
id
"gen-1771277125-raXYMo1MdwVHJ0v9F9DC"
upstream_id
"77f95e9a61c349ceb1bb05ab94ec46b6"
total_cost
0.000326764
cache_discount
1.08e-7
upstream_inference_cost
0
provider_name
"AtlasCloud"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9190%
Matches word count
n/a
neededClean
false
words
203
0.0002%
Dialogue to Total Word Ratio
Ratio: 70.94%, Deviation: 19.06%
neededClean
false
wordsTotal
203
wordsDialogue
144
49.9596%