NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5GT8FQVFK0FAFVBY2566F
Run Details
Model:
DeepSeek V3.2
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
12.7s
Cost:
$0.000149
Provider:
Novita
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
"Alright, run the plan by me again. My ears still hurt from the squeaky balloon animal demo," Bill said, rubbing his temple. "The target is a suburban home, the Johnson residence. The event is little Timmy Johnson's sixth birthday. Objective: extract all gift-wrapped assets," Molly stated. "Right. And the security?" "Negligible. One sleep-deprived parent, one over-sugared birthday boy, and approximately twelve miniature accomplices in Lightning McQueen t-shirts. Our window is during the cake-and-meltdown phase." Bill nodded. "Disguises?" "We pose as party entertainers. You're 'Grumpy the Clown.'" "I hate clowns." "That's why it's perfect. I'll be his harried assistant, 'Confetti,' maneuvering a large, hollow present-collection trunk." "Extraction?" "Load the trunk, wheel it to the 'clown car'—which is your actual car, Bill—and vanish before the piñata even swings." "What's the contingency for the parents?" "Misdirection. You'll accidentally-on-purpose release a dozen hyperactive puppies from the Johnson's garden shed. Chaos ensues. We profit." Bill sighed. "Stealing from kids, Molly. It feels… low." "These are luxury gifts, Bill! A tiny electric car, a junior virtual reality headset… We're practically redistributing wealth." "To ourselves." "Semantics. Are you in or not? The party starts in an hour." "I'm in. But I’m not making balloon poodles."
created_at
"2026-02-16T21:26:03.770338+00:00"
2/16/2026, 9:26:03 PM
model
"deepseek/deepseek-v3.2-20251201"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1145
moderation_latency
(null)
generation_time
12691
tokens_prompt
77
tokens_completion
375
native_tokens_prompt
67
native_tokens_completion
328
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
0.000149223
router
(null)
provider_responses
0
id
"45f61b477a00dd0368e9048d8d4a5d15"
status
200
is_byok
false
latency
1145
endpoint_id
"8a5fb6d3-ef71-4958-af54-269ffa3a3c6e"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-v3.2-20251201"
api_type
"completions"
id
"gen-1771277150-O5N4ElA43OHjU5glhXT2"
upstream_id
"45f61b477a00dd0368e9048d8d4a5d15"
total_cost
0.000149223
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
208
95.1917%
Dialogue to Total Word Ratio
Ratio: 94.71%, Deviation: 4.71%
neededClean
false
wordsTotal
208
wordsDialogue
197
95.5892%