NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5EVXD19JR0PTH3DTP6P09
Run Details
Model:
DeepSeek V3.2
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
44.7s
Cost:
$0.000158
Provider:
Parasail
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
“The target is a six-year-old’s birthday party,” Molly said, laying a hand-drawn map on the table. “A heist? Molly, it’s a yard full of toddlers.” “Precisely! Low security, predictable patterns. The mark—a ‘Super-Spy Sam’ action figure—will be in the blue-wrapped package. We need the whole haul for cover.” Bill stirred his coffee. “What’s the exfil strategy? Balloon animals?” “We go in as ‘Sparkle the Clown’ and her assistant. You’ll create a diversion.” “I’m not singing the banana song.” “You’ll sing it beautifully. During the second chorus, I’ll excuse myself to ‘refill the glitter.’ I’ll hit the gift table, stash the loot in the oversized clown car, and we vanish.” “What’s the primary obstacle?” “Vigilant parents. And a possible Labrador retriever named Buster.” Bill sighed. “Fine. But my clown name is ‘Mr. Fizzles,’ and I want a bigger cut.” “Sixty-forty. And you keep the wig.” “The pink one? Deal. What about the cake?” “No cake. This is a surgical strike.” “A surgical strike on a piñata.” “Focus, Bill. We go in at 1400 hours. Remember, the only thing louder than a crying child is a missing ‘Super-Spy Sam.’”
created_at
"2026-02-16T21:25:31.913073+00:00"
2/16/2026, 9:25:31 PM
model
"deepseek/deepseek-v3.2-20251201"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
907
moderation_latency
(null)
generation_time
44631
tokens_prompt
77
tokens_completion
346
native_tokens_prompt
67
native_tokens_completion
310
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
0.00015826
router
(null)
provider_responses
0
id
"d87fe8977e2b4c889190246c6abf0ee7"
status
200
is_byok
false
latency
907
endpoint_id
"4c18a672-9069-469d-9e6b-8af2300fe7b7"
provider_name
"Parasail"
model_permaslug
"deepseek/deepseek-v3.2-20251201"
api_type
"completions"
id
"gen-1771277086-TMYmaS3v2ZZbpLiJkVMI"
upstream_id
"d87fe8977e2b4c889190246c6abf0ee7"
total_cost
0.00015826
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Parasail"
Evaluation details
Result
Evaluator
Details
Meta Data
97.6276%
Matches word count
n/a
neededClean
false
words
193
99.9146%
Dialogue to Total Word Ratio
Ratio: 91.71%, Deviation: 1.71%
neededClean
false
wordsTotal
193
wordsDialogue
177
98.7711%