NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5FH6PPQPA9J4R7VAZ3YM3
Run Details
Model:
DeepSeek V3.2
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 2s
Cost:
$0.000151
Provider:
Phala
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 warehouse loft smelled of dust and desperation. Molly squinted at Bill’s blueprint, which was drawn on a napkin. A half-eaten doughnut served as a paperweight. “Okay,” Bill said, tapping the schematic. “The target is a six-year-old’s birthday party. The vault is a suburban living room. The security is… a chipper clown named Bubbles.” Molly pinched the bridge of her nose. “You want us to crash a kid’s party and swipe the gifts.” “Not crash. Infiltrate. You’ll go as the balloon-animal backup. I’ll be the disgruntled uncle, creating a diversion by ‘accidentally’ sitting on the cake.” “I can’t make balloon animals.” “Who can? You’ll just hand out long, wobbly balloons. The kids will be confused, not hostile. The real play is during the piñata. Chaos. We fill a sack and exit via the bounce house.” “The bounce house isn’t an exit, Bill. It’s an enclosed nylon prison.” “It’s tactical! We bounce over the fence. It’s genius.” Molly stared at the doughnut. “The take is what? Plastic dinosaurs and gift cards to toy stores?” “It’s the principle! A clean, low-stakes job to get our confidence back.” “Our last ‘low-stakes job’ was a lemonade stand. You got stung by a bee and confessed everything.” Bill folded the napkin with solemn dignity. “This time, no bees.”
created_at
"2026-02-16T21:26:11.189146+00:00"
2/16/2026, 9:26:11 PM
model
"deepseek/deepseek-v3.2-20251201"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1785
moderation_latency
(null)
generation_time
61762
tokens_prompt
77
tokens_completion
369
native_tokens_prompt
66
native_tokens_completion
332
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
0.00015062
router
(null)
provider_responses
0
id
"bd8c8df0f89e46c0b46fc3c8344d370e"
status
200
is_byok
false
latency
1785
endpoint_id
"4e9fb7e9-3967-4cd4-9723-df614f9f228e"
provider_name
"Phala"
model_permaslug
"deepseek/deepseek-v3.2-20251201"
api_type
"completions"
id
"gen-1771277108-CUYUKcwN3BuUlbcq8ryj"
upstream_id
"bd8c8df0f89e46c0b46fc3c8344d370e"
total_cost
0.00015062
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Phala"
Evaluation details
Result
Evaluator
Details
Meta Data
35.0022%
Matches word count
n/a
neededClean
false
words
218
0.0000%
Dialogue to Total Word Ratio
Ratio: 76.61%, Deviation: 26.61%
neededClean
false
wordsTotal
218
wordsDialogue
167
17.5011%