NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5R05GGQA0WBWCVBBWC4VS
Run Details
Model:
DeepSeek V3.2
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 8s
Cost:
$0.000148
Provider:
Phala
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
“Okay, the target is a six-year-old’s birthday party,” Molly said, spreading a crayon-drawn map on the table. “A kid’s party? What’s the take, half-eaten cake and sticky fingerprints?” “No, you philistine. The Smythe kid. Lavish gifts. Rumor has it there’s a solid gold rattle.” “A rattle? Bill, we don’t do rattles. We do jewels, bearer bonds.” “Think small, think adorable. High-end wooden toys, limited-edition stuffed animals. The resale market for nostalgic rich people is booming. We go in disguised as clowns.” “I’m not being a clown, Molly. I have a pathological fear of balloons.” “Fine. You’ll be the magician’s assistant. I’ll be the magician. During the big ‘disappearing rabbit’ trick, you’ll ‘accidentally’ knock over the gift table. Chaos ensues. We scoop and scoot.” “And the extraction?” “Piñata. We hollow it out, fill it with loot, and I’ll ‘triumphantly’ break it open. Parents will think the gifts are just fancy confetti. We walk out smiling.” Bill sighed. “This is a new low. Last month it was a museum. This month, a juice-box-fueled crime scene.” “It’s a soft target, Bill. The biggest threat is a soggy toddler with a loaded diaper. Now, can you fit into sequined hot pants?”
created_at
"2026-02-16T21:30:54.253286+00:00"
2/16/2026, 9:30:54 PM
model
"deepseek/deepseek-v3.2-20251201"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1513
moderation_latency
(null)
generation_time
67984
tokens_prompt
77
tokens_completion
349
native_tokens_prompt
66
native_tokens_completion
325
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
0.00014782
router
(null)
provider_responses
0
id
"d3934b39ecaf411c880ac33ea07c331d"
status
200
is_byok
false
latency
1513
endpoint_id
"4e9fb7e9-3967-4cd4-9723-df614f9f228e"
provider_name
"Phala"
model_permaslug
"deepseek/deepseek-v3.2-20251201"
api_type
"completions"
id
"gen-1771277385-a1aFuP6oI1dLQjDkAiW3"
upstream_id
"d3934b39ecaf411c880ac33ea07c331d"
total_cost
0.00014782
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Phala"
Evaluation details
Result
Evaluator
Details
Meta Data
99.3769%
Matches word count
n/a
neededClean
false
words
205
97.0876%
Dialogue to Total Word Ratio
Ratio: 94.15%, Deviation: 4.15%
neededClean
false
wordsTotal
205
wordsDialogue
193
98.2323%