NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5J9PX75Z72H37YXQ05N8Y
Run Details
Model:
DeepSeek V3.2
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
9.3s
Cost:
$0.000125
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 traced a pudgy finger across the birthday party flyer, the glitter smudging under her touch. “Balloon animals are a structural weakness,” she stated, pointing to a sketched poodle. Beside her, Bill polished a monocle that served no corrective purpose. The warehouse loft was their war room. A diagram of the suburban backyard was pinned between peeling posters of famous art heists. Their tools lay in orderly rows: wire cutters for ribbon, a silent leaf-blower to disperse nosy parents, and a harness to lower Bill, the smaller of the two, down the chimney they presumed existed. Bill adjusted his fake moustache. “The cake is a seven-layer vanilla fortress. It demands respect.” He proposed a diversion involving a rogue piñata and three grams of industrial-grade glitter. Molly nodded, her eyes on the primary objective: a mountain of wrapped boxes near the swing set. She envisioned the haul: plastic treasures, gift cards, the whispered legend of a limited-edition action figure. It was petty, but glorious. “Remember,” she whispered, the only sound in the dusty room. “No waking the toddler. That’s when they get… unpredictable.” Bill gave a solemn nod. The clock ticked toward naptime. Operation Sugar Rush was a go.
created_at
"2026-02-16T21:26:49.070241+00:00"
2/16/2026, 9:26:49 PM
model
"deepseek/deepseek-v3.2-20251201"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1188
moderation_latency
(null)
generation_time
9257
tokens_prompt
77
tokens_completion
325
native_tokens_prompt
67
native_tokens_completion
268
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
0.000125223
router
(null)
provider_responses
0
id
"9311730c21142fd4b1b1be19b10c7cad"
status
200
is_byok
false
latency
1188
endpoint_id
"8a5fb6d3-ef71-4958-af54-269ffa3a3c6e"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-v3.2-20251201"
api_type
"completions"
id
"gen-1771277199-MNLkabzF0rKMuugloL9a"
upstream_id
"9311730c21142fd4b1b1be19b10c7cad"
total_cost
0.000125223
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9840%
Matches word count
n/a
neededClean
false
words
202
98.7240%
Dialogue to Total Word Ratio
Ratio: 13.37%, Deviation: 3.37%
neededClean
false
wordsTotal
202
wordsDialogue
27
99.3540%