NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM6248Q0088F8XWRYW95J7E
Run Details
Model:
DeepSeek V3 (2024-12-26)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
14.1s
Cost:
$0.000327
Provider:
DeepInfra
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
“Did you say children’s party?” Molly asked, squinting at Bill across the dimly lit diner booth. “Yeah,” Bill replied, stirring his coffee with a bent spoon. “Bunch of cake, piñatas, and presents wrapped in shiny paper. It’s perfect.” “Perfect? Bill, we’re stealing from kids. That’s like robbing a lemonade stand—lowest of the low.” “It’s not about morality, Molly. It’s about opportunity. Think about it. Kids’ presents are small, portable, and always top-tier. Legos, action figures, maybe even a PS5 if we’re lucky.” “And you’re sure security won’t be tight?” “Tight? It’s a birthday party. The biggest threat is a hyperactive clown and a mom armed with a juice box.” “What if the clown gets suspicious?” “Clowns are paid to entertain, not interrogate. We show up in costumes—boom, instant invisibility.” “What kind of costumes?” “I’m thinking superheroes. You can be Wonder Woman, I’ll be Batman.” “Batman doesn’t steal, Bill.” “He does if he’s broke. Look, are you in or not?” Molly sighed, rubbing her temples. “Fine. But if we get caught, I’m telling them you masterminded this.” “Fair enough. Now, finish your fries—we’ve got a piñata to crack.” “You mean *plan* to crack.” “Same thing.”
created_at
"2026-02-16T21:35:32.436365+00:00"
2/16/2026, 9:35:32 PM
model
"deepseek/deepseek-chat-v3"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
216
moderation_latency
(null)
generation_time
14024
tokens_prompt
77
tokens_completion
360
native_tokens_prompt
66
native_tokens_completion
344
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
0.00032728
router
(null)
provider_responses
0
id
"chatcmpl-RjEwdnkfoUEUuQgFHDpTfJqd"
status
200
is_byok
false
latency
52
endpoint_id
"5294d55f-9012-496b-8f22-8cc919432dcd"
provider_name
"DeepInfra"
model_permaslug
"deepseek/deepseek-chat-v3"
api_type
"completions"
id
"gen-1771277717-z0r2q6JepGRMqi8oMWPB"
upstream_id
"chatcmpl-RjEwdnkfoUEUuQgFHDpTfJqd"
total_cost
0.00032728
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9840%
Matches word count
n/a
neededClean
false
words
198
99.5254%
Dialogue to Total Word Ratio
Ratio: 87.37%, Deviation: 2.63%
neededClean
false
wordsTotal
198
wordsDialogue
173
99.7547%