NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM60997YXRY0W8YRGYZAD9J
Run Details
Model:
DeepSeek V3 (2025-03-24)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
7.4s
Cost:
$0.000349
Provider:
Novita
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
“You sure this is a good idea?” Bill adjusted his fake mustache in the rearview mirror. “Relax,” Molly said, tossing him a neon party hat. “Kids’ birthday parties are the easiest scores. No one suspects the clown.” “You’re not dressed as a clown.” “I’m wearing suspenders and rainbow socks. That’s clown-adjacent.” Molly unfolded a crinkled map of the backyard. “Presents are stacked by the pinata. We grab, we go.” “What about security?” “The only muscle there is a six-year-old named Timmy who thinks he’s a dinosaur.” Bill sighed. “Last time you said ‘no security,’ it was a retired K-9 unit.” “That dog just wanted belly rubs. Besides, this is foolproof. Everyone’s distracted by cake and tears.” “What if we get caught?” Molly rolled her eyes. “We’ll say we’re estranged relatives. No one remembers all the aunts and uncles.” Bill hesitated. “I dunno. Feels wrong stealing from kids.” “They’re rich kids, Bill. The gifts are all iPads and ponies.” “Ponies don’t fit in the getaway car.” Molly grinned. “That’s why we’re taking the bouncy castle truck.”
created_at
"2026-02-16T21:34:25.418238+00:00"
2/16/2026, 9:34:25 PM
model
"deepseek/deepseek-chat-v3-0324"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
327
moderation_latency
(null)
generation_time
7174
tokens_prompt
77
tokens_completion
328
native_tokens_prompt
69
native_tokens_completion
295
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
0.00034903
router
(null)
provider_responses
0
status
429
is_byok
false
latency
128
endpoint_id
"eb0625b2-17a1-492d-b3cc-e35091f1431d"
provider_name
"Crusoe"
model_permaslug
"deepseek/deepseek-chat-v3-0324"
1
id
"158658039847935263cec560a46e8c8f"
status
200
is_byok
false
latency
327
endpoint_id
"3a816eb8-7a0b-4a9a-b497-e3a1efb349fc"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-chat-v3-0324"
api_type
"completions"
id
"gen-1771277657-iH8Vy8AODR5khy9DThUq"
upstream_id
"158658039847935263cec560a46e8c8f"
total_cost
0.00034903
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
9.6081%
Matches word count
n/a
neededClean
false
words
178
41.8184%
Dialogue to Total Word Ratio
Ratio: 80.34%, Deviation: 9.66%
neededClean
false
wordsTotal
178
wordsDialogue
143
25.7133%