NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5WDYYKVQ9F1HVYK9FX953
Run Details
Model:
DeepSeek V3 (2024-12-26)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
12.3s
Cost:
$0.000419
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
Molly adjusted her fake mustache and squinted at the party invitation. “Bill, are you sure this is the right address?” Bill tugged at his clown suit, which was two sizes too small. “Positive. Little Timmy’s sixth birthday. Rich kid, rich presents. It’s foolproof.” “We’re dressed as a clown and a magician, Bill. We’re the fools.” “Relax. Kids love clowns.” “Kids *fear* clowns. And magicians. And people who show up uninvited.” Bill waved her off. “We’re ‘entertainers.’ They’ll be so dazzled by my balloon animals, they won’t even notice you stuffing the gifts into your oversized hat.” Molly sighed. “Fine. But if we get caught, I’m blaming you.” “Deal. Now, remember the plan: distract, grab, and—” “—run like hell when the parents realize we’re not the hired help.” Bill grinned. “Exactly. Oh, and one more thing.” He handed her a whoopee cushion. Molly stared at it. “What’s this for?” “Diversion. Pop it during the cake cutting. Chaos ensues.” “You’re a genius.” “I know.” Molly pocketed the cushion. “Let’s go steal some Legos.”
created_at
"2026-02-16T21:32:24.057661+00:00"
2/16/2026, 9:32:24 PM
model
"deepseek/deepseek-chat-v3"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1425
moderation_latency
(null)
generation_time
12234
tokens_prompt
77
tokens_completion
325
native_tokens_prompt
66
native_tokens_completion
302
native_tokens_completion_images
0
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
0.000419
router
(null)
provider_responses
0
id
"569154ccb72293889bb577d4235c9ca7"
status
200
is_byok
false
latency
1425
endpoint_id
"cefb5a1e-9fea-4496-9a64-4e1b11a7cc8c"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-chat-v3"
api_type
"completions"
id
"gen-1771277531-M9NIdIc77xAxbNp5MCR0"
upstream_id
"569154ccb72293889bb577d4235c9ca7"
total_cost
0.000419
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
0.0848%
Matches word count
n/a
neededClean
false
words
171
0.0836%
Dialogue to Total Word Ratio
Ratio: 73.68%, Deviation: 16.32%
neededClean
false
wordsTotal
171
wordsDialogue
126
0.0842%