NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5DX15EEM62BTK1ZPE4CDT
Run Details
Model:
DeepSeek V3.1
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
8.4s
Cost:
$0.000287
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 peeked from behind the oak tree, the brightly colored bouncy castle casting a garish glow on her face. “It’s worse than the Frankfurt Diamond Exchange,” she whispered. Bill, fiddling with a lockpick shaped like a cartoon dolphin, grumbled. “The security is terrifying. I counted seven juice-stained toddlers with the lung capacity of air raid sirens.” “Forget the toddlers. The real threat is Brenda, the birthday girl’s grandmother. She has the eyes of a hawk and the resting face of a betrayed librarian.” Molly pointed a trembling finger. “She’s guarding the gift table like it’s the royal mint.” “So what’s the play?” “Distraction. You create a minor frosting-related incident at the cake station. I sneak in, swap the presents for these,” she said, holding up a bag of identically wrapped boxes, “which are tragically filled with educational flashcards and sensible socks.” “A victimless crime!” Bill grinned. “They’ll be thanking us in fifteen years.” He adjusted his fake moustache. “Okay. On three, I fake a catastrophic stumble into the chocolate fountain. Ready?” Molly sighed. “Just try to make it look like an accident. We’re professionals, Bill. Mostly.”
created_at
"2026-02-16T21:24:24.308833+00:00"
2/16/2026, 9:24:24 PM
model
"deepseek/deepseek-chat-v3.1"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1025
moderation_latency
(null)
generation_time
8273
tokens_prompt
95
tokens_completion
326
native_tokens_prompt
68
native_tokens_completion
269
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
0.00028736
router
(null)
provider_responses
0
id
"73d0487c-2dad-4c0a-92c8-5b281b26fc57"
status
200
is_byok
false
latency
1025
endpoint_id
"715d05e1-9fa7-4ceb-834a-833f5e26a55a"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-chat-v3.1"
api_type
"completions"
id
"gen-1771277055-l6vKog1QQpMRtVq25pQr"
upstream_id
"73d0487c-2dad-4c0a-92c8-5b281b26fc57"
total_cost
0.00028736
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
81.2727%
Matches word count
n/a
neededClean
false
words
188
0.0000%
Dialogue to Total Word Ratio
Ratio: 70.21%, Deviation: 20.21%
neededClean
false
wordsTotal
188
wordsDialogue
132
40.6364%