NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5BB441E4411BG0J4S94R3
Run Details
Model:
DeepSeek V3 (2024-12-26)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
9.7s
Cost:
$0.000454
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 oversized clown nose, glaring at Bill over the top of her rainbow wig. “This is the worst disguise ever,” she muttered, tugging at the polka-dot suspenders digging into her shoulders. Bill, sporting a lopsided unicorn horn and a tutu, grinned. “Relax. Kids love clowns. And unicorns. Mostly.” He unfolded a crumpled napkin—their “blueprint”—covered in crayon scribbles and frosting stains. “Okay, so the presents are by the piñata. We grab ’em during the chaos.” Molly eyed the backyard swarming with sugar-crazed six-year-olds. “Chaos? You mean when the birthday kid swings a bat like a maniac?” “Exactly.” Bill patted his oversized gift bag. “We blend in, load up, and vanish before anyone notices.” A shriek erupted as the piñata split open, candy raining down. Kids dove like tiny, feral raccoons. Molly elbowed Bill. “Now!” They lunged for the gift pile, stuffing presents into the bag. A toddler in a superhero cape pointed. “That unicorn’s stealing!” Bill froze. Molly grabbed his arm. “Run!” They bolted, tutu flapping, clown shoes squeaking, as a chorus of tiny voices chased them with cries of “Stop, unicorn thief!” Rounding the corner, Bill wheezed. “Next time… no costumes.” Molly tossed the wig into a bush. “Next time… no kids.”
created_at
"2026-02-16T21:23:01.364563+00:00"
2/16/2026, 9:23:01 PM
model
"deepseek/deepseek-chat-v3"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
929
moderation_latency
(null)
generation_time
9346
tokens_prompt
77
tokens_completion
362
native_tokens_prompt
66
native_tokens_completion
329
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
0.0004541
router
(null)
provider_responses
0
id
"8b12f2c85335a2cd23f314b625ba615b"
status
200
is_byok
false
latency
929
endpoint_id
"cefb5a1e-9fea-4496-9a64-4e1b11a7cc8c"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-chat-v3"
api_type
"completions"
id
"gen-1771276971-RmHYdnqg2pvVH3Jt2B1b"
upstream_id
"8b12f2c85335a2cd23f314b625ba615b"
total_cost
0.0004541
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
93.6496%
Matches word count
n/a
neededClean
false
words
209
0.0000%
Dialogue to Total Word Ratio
Ratio: 35.41%, Deviation: 25.41%
neededClean
false
wordsTotal
209
wordsDialogue
74
46.8248%