NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM61WCQ2QCF0474V11W4W6Z
Run Details
Model:
DeepSeek V3 (2024-12-26)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
11.3s
Cost:
$0.000415
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
Molly adjusted the fake mustache that kept peeling at one corner while Bill squinted at the scribbled map of the backyard. The plan was simple: sneak in during the chaos of the piñata explosion, grab the presents, and vanish before anyone noticed the loot was gone. “You sure this’ll work?” Bill whispered, eyeing the inflatable bouncy castle like it might bite him. “Trust me,” Molly said, shoving a handful of confetti into her pocket as a distraction tactic. “No one suspects clowns.” Bill groaned. “We’re not dressed as clowns.” “Close enough.” The party was in full swing—screaming children, harried parents, and a dog wearing a party hat. Molly nudged Bill toward the gift table, where a mountain of brightly wrapped boxes taunted them. “Just grab and go,” she muttered. Bill reached for a present shaped like a dinosaur. A tiny hand slapped his wrist. “That’s mine,” a child said, glaring. Bill froze. Molly coughed loudly and tossed the confetti into the air. “Happy birthday!” she bellowed, yanking Bill away as the crowd cheered. They sprinted to the fence, empty-handed. “New plan,” Bill wheezed. “No more kids’ parties.” Molly sighed. “Fine. Next time, we rob a bank.”
created_at
"2026-02-16T21:35:21.814562+00:00"
2/16/2026, 9:35:21 PM
model
"deepseek/deepseek-chat-v3"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1164
moderation_latency
(null)
generation_time
11248
tokens_prompt
77
tokens_completion
343
native_tokens_prompt
66
native_tokens_completion
299
native_tokens_completion_images
0
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
0.0004151
router
(null)
provider_responses
0
id
"19800af60e577c2c2eb8860119cc8f76"
status
200
is_byok
false
latency
1164
endpoint_id
"cefb5a1e-9fea-4496-9a64-4e1b11a7cc8c"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-chat-v3"
api_type
"completions"
id
"gen-1771277709-SlR7eWMp8hOuENfShSj2"
upstream_id
"19800af60e577c2c2eb8860119cc8f76"
total_cost
0.0004151
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9840%
Matches word count
n/a
neededClean
false
words
198
48.9741%
Dialogue to Total Word Ratio
Ratio: 19.19%, Deviation: 9.19%
neededClean
false
wordsTotal
198
wordsDialogue
38
74.4790%