NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM60NVXS4JDK5SQG8EXFP3A
Run Details
Model:
DeepSeek V3.1
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
8.9s
Cost:
$0.000304
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
Bill traced a pudgy finger over the cupcake-strewn layout of 14 Elm Street. “The target is a fortress of whimsy, Molly. A real nightmare of pastel decorations.” Molly polished a lockpick with her sleeve. “It’s a six-year-old’s birthday party, Bill. The biggest threat is a sugar-crazed toddler.” “Precisely! Unpredictable little agents of chaos.” Bill pointed dramatically to a sketched-in bouncy castle. “Our primary obstacle. It blocks the primary path from the gift table to our extraction vehicle.” “We go under it. It’s inflatable.” “And risk a structural failure? We’d be entombed in vinyl.” He shuddered. “No, we need a distraction.” Molly sighed, grabbing two brightly wrapped boxes from a shelf. “We’re the clowns, Bill. Remember? We’re invited. We just walk in, do the stupid balloon animal bit, and walk out with the loot.” Bill’s eyes widened with panic. “Balloon animals? The briefing said nothing about mandatory artistry. My poodle looks like a mutated slug.” “Then make a snake. It’s just a tube.” Molly tossed him a garish, multi-colored wig. “Now get in character. And for God’s sake, try to look like you enjoy children.”
created_at
"2026-02-16T21:34:40.119904+00:00"
2/16/2026, 9:34:40 PM
model
"deepseek/deepseek-chat-v3.1"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
925
moderation_latency
(null)
generation_time
8656
tokens_prompt
95
tokens_completion
321
native_tokens_prompt
68
native_tokens_completion
286
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
0.00030436
router
(null)
provider_responses
0
status
429
is_byok
false
latency
48
endpoint_id
"012f7d1f-23d4-4d03-9aa3-432d8ad82757"
provider_name
"DeepInfra"
model_permaslug
"deepseek/deepseek-chat-v3.1"
1
id
"f55510cc-bc73-44e2-af30-5614c326f2c2"
status
200
is_byok
false
latency
925
endpoint_id
"715d05e1-9fa7-4ceb-834a-833f5e26a55a"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-chat-v3.1"
api_type
"completions"
id
"gen-1771277670-o5Z9Tgid4XaBT5q1i0Zu"
upstream_id
"f55510cc-bc73-44e2-af30-5614c326f2c2"
total_cost
0.00030436
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
86.3803%
Matches word count
n/a
neededClean
false
words
189
0.0000%
Dialogue to Total Word Ratio
Ratio: 71.43%, Deviation: 61.43%
neededClean
false
wordsTotal
189
wordsDialogue
135
43.1902%