NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5Q6MHNSTPRNWTXQ1RXJN3
Run Details
Model:
DeepSeek V3 (2024-12-26)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
11.4s
Cost:
$0.000337
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
The dim glow of a flickering bulb illuminated the cramped, dusty attic where Molly and Bill hunched over a crinkled map of the neighborhood. Molly tapped the paper with a chipped fingernail. “The party’s at 3 p.m. sharp. Kids’ll be hopped up on sugar, parents will be distracted, and the presents? Right there—begging to be liberated.” Bill squinted, scratching his scruffy chin. “Liberated? Molly, it’s a kiddie party. We’re talking crayons and Lego sets, not the Crown Jewels.” Molly smirked, adjusting her black beanie. “Details, Bill. Details. It’s not about the loot; it’s about the challenge. No alarms, no guards—just us versus a piñata.” Bill groaned. “Piñatas are unpredictable. Those things swing back.” “You’re afraid of candy?” Molly rolled her eyes. “Look, here’s the plan: I’ll dress as a clown. Kids love clowns.” “Kids *hate* clowns,” Bill countered. “You’ll give ’em nightmares.” Molly waved him off. “Fine, I’ll be a magician. I’ll distract them with card tricks while you grab the goods.” Bill sighed, rubbing his temple. “You realize this is the worst idea we’ve ever had, right?” Molly grinned. “Worse than the hamster heist?” “Fair point,” Bill conceded. “But if we get caught, I’m blaming the piñata.” “Deal,” Molly said, folding the map. “Now let’s go steal some joy.”
created_at
"2026-02-16T21:29:31.96238+00:00"
2/16/2026, 9:29:31 PM
model
"deepseek/deepseek-chat-v3"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
402
moderation_latency
(null)
generation_time
11376
tokens_prompt
77
tokens_completion
379
native_tokens_prompt
66
native_tokens_completion
355
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
0.00033707
router
(null)
provider_responses
0
id
"chatcmpl-RSrT1kXt2Kk02IuzlYanNTSF"
status
200
is_byok
false
latency
53
endpoint_id
"5294d55f-9012-496b-8f22-8cc919432dcd"
provider_name
"DeepInfra"
model_permaslug
"deepseek/deepseek-chat-v3"
api_type
"completions"
id
"gen-1771277359-MVvZv3y0y794hCp1cBQW"
upstream_id
"chatcmpl-RSrT1kXt2Kk02IuzlYanNTSF"
total_cost
0.00033707
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
81.2727%
Matches word count
n/a
neededClean
false
words
212
0.0245%
Dialogue to Total Word Ratio
Ratio: 66.98%, Deviation: 16.98%
neededClean
false
wordsTotal
212
wordsDialogue
142
40.6486%