NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM617RFT3QCT7MWGTP61BEM
Run Details
Model:
DeepSeek V3 (2025-03-24)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
9.9s
Cost:
$0.000358
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
The dim glow of a single naked bulb flickered above Molly and Bill as they hunched over a crudely drawn map of the Smythe family backyard. Balloon arches, a bouncy castle, and a suspiciously well-guarded gift table were labeled with the urgency of a military operation. Molly tapped a red X with her chewed-up pencil. “Guard dog,” she muttered. Bill squinted. “That’s a chihuahua in a party hat.” Molly glared. “It’s got the eyes of a killer.” Bill sighed, rubbing the stubble on his chin. “Alright, so we distract the dog with cake, slip in during the piñata chaos—” “No, no, no,” Molly interrupted, “the piñata’s a decoy. The real play is the magician. Crowd’s hypnotized, we grab the loot, disappear like bad magic.” Bill frowned. “You think a guy who can’t even pull a rabbit out of a hat is gonna hypnotize anyone?” Molly leaned in, grinning. “Exactly. Kids’ll be so disappointed, they won’t notice us.” Outside, the distant squeal of children echoed. Bill chewed his lip. “What if we get caught?” Molly snatched the map. “Then we blame the clown.” The bulb buzzed. Somewhere, a chihuahua barked. The heist was on.
created_at
"2026-02-16T21:34:59.014575+00:00"
2/16/2026, 9:34:59 PM
model
"deepseek/deepseek-chat-v3-0324"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
303
moderation_latency
(null)
generation_time
9801
tokens_prompt
77
tokens_completion
318
native_tokens_prompt
69
native_tokens_completion
303
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
0.00035799
router
(null)
provider_responses
0
id
"2ad5dd79eb3092a33d4d7274ac8d0815"
status
200
is_byok
false
latency
303
endpoint_id
"3a816eb8-7a0b-4a9a-b497-e3a1efb349fc"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-chat-v3-0324"
api_type
"completions"
id
"gen-1771277688-MUwW8fm3f2riG0idBnh9"
upstream_id
"2ad5dd79eb3092a33d4d7274ac8d0815"
total_cost
0.00035799
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
99.3769%
Matches word count
n/a
neededClean
false
words
195
0.0000%
Dialogue to Total Word Ratio
Ratio: 46.15%, Deviation: 36.15%
neededClean
false
wordsTotal
195
wordsDialogue
90
49.6885%