NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5QQ3AQDVWAGK7B0JTTQCK
Run Details
Model:
DeepSeek V3.2
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
8.0s
Cost:
$0.000126
Provider:
Novita
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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
Molly squinted at the garishly colored invitation taped to the dashboard. "The Waverly estate. Noon tomorrow. Theme: Unicorn Princess." Beside her, Bill adjusted a pair of fake spectacles, studying the corresponding blueprint. "Security’s a nap-time monitor and a hyper-vigilant poodle named Sprinkles. The haul is in the 'Throne Room,' east patio." Their van, smelling of stale coffee and desperation, was parked two blocks over. Molly traced the route on the map. "Ingress is the side gate, disguised as the glitter delivery. Egress via the bouncy castle deflation." "Risky," Bill muttered, tapping the castle schematic. "Timing is critical." "The real variable is the cake," Molly said, her tone grave. "A three-tiered rainbow sponge. Distraction occurs during the sugar rush peak, when the tiny monarch is fully engrossed in fondant." Bill allowed himself a thin smile, imagining the chaos. They sat in silence for a moment, the weight of their absurd ambition hanging between them. Outside, a normal street carried on with its normal day, oblivious to the plot unfolding in the shabby van. They were going to rob a six-year-old, and the plan was, against all reason, solid.
created_at
"2026-02-16T21:29:45.36741+00:00"
2/16/2026, 9:29:45 PM
model
"deepseek/deepseek-v3.2-20251201"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
953
moderation_latency
(null)
generation_time
7935
tokens_prompt
77
tokens_completion
304
native_tokens_prompt
67
native_tokens_completion
270
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
0.000126023
router
(null)
provider_responses
0
id
"ee09bd5dd1547d04bf25d46d8d743e41"
status
200
is_byok
false
latency
953
endpoint_id
"8a5fb6d3-ef71-4958-af54-269ffa3a3c6e"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-v3.2-20251201"
api_type
"completions"
id
"gen-1771277376-dDA2U5V2NVS0jIJKRege"
upstream_id
"ee09bd5dd1547d04bf25d46d8d743e41"
total_cost
0.000126023
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
95.9868%
Matches word count
n/a
neededClean
false
words
192
0.0000%
Dialogue to Total Word Ratio
Ratio: 39.58%, Deviation: 29.58%
neededClean
false
wordsTotal
192
wordsDialogue
76
47.9934%