NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM62P9JWZFE6VMAYJNA2AY2
Run Details
Model:
DeepSeek V3 (2025-03-24)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
6.9s
Cost:
$0.000376
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 party decorations flapped in the breeze like surrender flags, taunting Molly and Bill from their stakeout spot behind a hedge. Molly adjusted her oversized sunglasses—disguised as a concerned aunt—while Bill nibbled on a stolen cupcake, frosting smeared on his chin like a toddler’s failed art project. “We go in during the piñata chaos,” Molly whispered. Bill frowned. “What if the kids cry?” “That’s the beauty of it—no one notices more screaming at a kid’s party.” Inside, a clown twisted balloons into questionable shapes while parents sipped lukewarm coffee, their exhaustion palpable. The presents sat in a glittering pile, guarded only by a six-year-old in a superhero cape. Bill wiped his hands on his pants. “I dunno, Moll. Feels wrong.” “Stealing from a bank feels wrong. This is just…redistributing holiday cheer.” A sudden shriek erupted as the piñata burst, candy raining down. Molly seized the moment, darting forward with a trash bag disguised as a gift. Bill hesitated, then followed, tripping over a discarded juice box. “Smooth,” Molly muttered, shoving a present into the bag. “I’ve got morals!” Bill hissed, righting himself. “Then carry the loot and repent later.” The superhero kid blinked at them. Bill tossed him a candy bar. “Distraction tactics,” he explained. Molly rolled her eyes and kept stealing.
created_at
"2026-02-16T21:35:43.530848+00:00"
2/16/2026, 9:35:43 PM
model
"deepseek/deepseek-chat-v3-0324"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
838
moderation_latency
(null)
generation_time
6894
tokens_prompt
77
tokens_completion
379
native_tokens_prompt
69
native_tokens_completion
319
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
0.00037591
router
(null)
provider_responses
0
id
"b6197eb313750d6556e4377d3d18ac90"
status
200
is_byok
false
latency
838
endpoint_id
"3a816eb8-7a0b-4a9a-b497-e3a1efb349fc"
provider_name
"Novita"
model_permaslug
"deepseek/deepseek-chat-v3-0324"
api_type
"completions"
id
"gen-1771277736-DxfpULsZPVbnSxNHnJfx"
upstream_id
"b6197eb313750d6556e4377d3d18ac90"
total_cost
0.00037591
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Novita"
Evaluation details
Result
Evaluator
Details
Meta Data
43.3783%
Matches word count
n/a
neededClean
false
words
217
0.3905%
Dialogue to Total Word Ratio
Ratio: 25.35%, Deviation: 15.35%
neededClean
false
wordsTotal
217
wordsDialogue
55
21.8844%