NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5HWN1ZRC0RNMHNWTJG4JK
Run Details
Model:
DeepSeek V3 (2025-03-24)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
8.1s
Cost:
$0.000278
Provider:
AtlasCloud
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 adjusted her fake clown nose and sighed. “Bill, I still think this is a bad idea.” Bill tightened his rainbow wig, the curls bouncing with misplaced enthusiasm. “Relax. No one suspects the entertainment.” He gestured to the van stuffed with balloons and a piñata shaped like a unicorn—its hollow belly perfect for stashing loot. The neighborhood bouncy castle loomed ahead, a beacon of reckless childhood joy. Molly grimaced. “We’re stealing from toddlers. That’s a new low.” “Technically, we’re stealing from their parents,” Bill corrected, tapping a party invitation against his palm. “And they’ve got insurance.” A distant squeal of laughter made Molly wince. “What if we get caught?” “Then we’ll have the greatest escape story ever. ‘Daring Duo Flees on Big Wheel.’” Bill tossed her a rubber chicken for emphasis. Molly caught it with a grumble. “Fine. But if we end up in a high-speed chase with a cupcake truck, I’m blaming you.” Bill adjusted his neon suspenders and grinned. “That’s the spirit! Now help me with this magician’s box. It’s our ticket to disappearing—after we empty the gift table.” Molly muttered something uncharitable under her breath but grabbed the other end of the box. The heist was on.
created_at
"2026-02-16T21:26:34.536327+00:00"
2/16/2026, 9:26:34 PM
model
"deepseek/deepseek-chat-v3-0324"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
822
moderation_latency
(null)
generation_time
8028
tokens_prompt
77
tokens_completion
348
native_tokens_prompt
67
native_tokens_completion
301
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
0.000278488
router
(null)
provider_responses
0
id
"2f424a137fa44c1a934035cdc2bfc830"
status
200
is_byok
false
latency
822
endpoint_id
"5bb598f5-fd97-4f8b-91e4-ceab3743a03b"
provider_name
"AtlasCloud"
model_permaslug
"deepseek/deepseek-chat-v3-0324"
api_type
"completions"
id
"gen-1771277185-RX0TYkbRU0B7MndiAwCn"
upstream_id
"2f424a137fa44c1a934035cdc2bfc830"
total_cost
0.000278488
cache_discount
8.64e-7
upstream_inference_cost
0
provider_name
"AtlasCloud"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9190%
Matches word count
n/a
neededClean
false
words
203
0.0000%
Dialogue to Total Word Ratio
Ratio: 44.83%, Deviation: 34.83%
neededClean
false
wordsTotal
203
wordsDialogue
91
49.9595%