NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5QRJ5WY5BGTJSMK89WNN1
Run Details
Model:
DeepSeek V3 (2025-03-24)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
47.4s
Cost:
$0.000308
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
The inflatable clown sneered at Molly from the corner of the party supply warehouse, its painted grin mocking her current predicament. She tossed a grappling hook from hand to hand, eyes darting across the blueprint of the Thompson’s backyard—so many obstacles, so little time. Bill, ever the optimist, was busy stuffing his pockets with confetti bombs. "We’re stealing from a six-year-old’s birthday?" Molly hissed. Bill adjusted his fake mustache, which was already peeling. "Biggest haul of the season. You heard the rumors—gold-plated LEGOs, designer teddy bears." Molly sighed as she ran a finger along the blueprint’s dotted lines. "Guards?" "Two. The clown and the magician." "The clown’s just a guy in face paint." "Still terrifying." A beat passed. Molly folded the blueprint. "What’s the play?" Bill grinned. "You distract them with a tragic balloon animal. I’ll grab the loot and meet you at the bounce house exit." Molly pinched the bridge of her nose. "This is the dumbest plan we’ve ever had." Bill winked. "Best one, too."
created_at
"2026-02-16T21:30:25.961388+00:00"
2/16/2026, 9:30:25 PM
model
"deepseek/deepseek-chat-v3-0324"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1056
moderation_latency
(null)
generation_time
47361
tokens_prompt
77
tokens_completion
290
native_tokens_prompt
69
native_tokens_completion
258
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
0.00030759
router
(null)
provider_responses
0
id
"cab69dc98f5a956a22ce6e067d3f63a2"
status
200
is_byok
false
latency
1055
endpoint_id
"3a816eb8-7a0b-4a9a-b497-e3a1efb349fc"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-chat-v3-0324"
api_type
"completions"
id
"gen-1771277378-KlUqg6PV6LNznJTFKzfJ"
upstream_id
"cab69dc98f5a956a22ce6e067d3f63a2"
total_cost
0.00030759
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
0.2141%
Matches word count
n/a
neededClean
false
words
172
0.0000%
Dialogue to Total Word Ratio
Ratio: 43.02%, Deviation: 33.02%
neededClean
false
wordsTotal
172
wordsDialogue
74
0.1070%