NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5C4R7ZY8VXMBN73EV3MKJ
Run Details
Model:
DeepSeek V3 (2024-12-26)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
11.2s
Cost:
$0.000307
Provider:
DeepInfra
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 adjusted her pink party hat in the rearview mirror, scowling. “Bill, this plan is insane. We’re supposed to blend in at a kids’ party? You realize we stick out like raccoons at a cat show, right?” Bill grinned, his fake mustache crooked. “Relax, Moll. Nobody’s gonna suspect us. We’re the entertainment. The magicians. Who doesn’t love magicians?” “Magicians who steal presents?” Molly shot back, smoothing her oversized clown shirt. “That’s not magic, Bill. That’s just theft with glitter.” “Exactly!” Bill said, snapping his fingers. “It’s a twist. We’ll dazzle ‘em with card tricks, and while they’re distracted, we load the gifts into the van. Easy peasy lemon squeezy.” “Easy peasy lemon squeezy?” Molly groaned. “You sound like a sitcom dad from the ’90s.” “Hey, I’m improvising here!” Bill protested. “Besides, it’ll work. Trust me.” Molly sighed, glancing at the stack of fake balloons in the backseat. “Fine. But if one of those kids catches us, you’re buying me tacos for a month.” “Deal,” Bill said, adjusting his bowtie. “Now, let’s go make some birthday magic—chaos optional.” They exchanged a nod, stepped out of the van, and marched toward the house, their oversized shoes squeaking with every step.
created_at
"2026-02-16T21:23:29.465784+00:00"
2/16/2026, 9:23:29 PM
model
"deepseek/deepseek-chat-v3"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
301
moderation_latency
(null)
generation_time
11151
tokens_prompt
77
tokens_completion
352
native_tokens_prompt
66
native_tokens_completion
321
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
0.00030681
router
(null)
provider_responses
0
id
"chatcmpl-R62JDp15huFG1e1lSOUAmQd9"
status
200
is_byok
false
latency
47
endpoint_id
"5294d55f-9012-496b-8f22-8cc919432dcd"
provider_name
"DeepInfra"
model_permaslug
"deepseek/deepseek-chat-v3"
api_type
"completions"
id
"gen-1771276997-T2mWf4Zh0ElIBhz2fJOd"
upstream_id
"chatcmpl-R62JDp15huFG1e1lSOUAmQd9"
total_cost
0.00030681
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9990%
Matches word count
n/a
neededClean
false
words
199
2.6073%
Dialogue to Total Word Ratio
Ratio: 63.82%, Deviation: 13.82%
neededClean
false
wordsTotal
199
wordsDialogue
127
51.3032%