NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5ZAB2SAS0285365FXTVGP
Run Details
Model:
DeepSeek V3 (2025-03-24)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
13.0s
Cost:
$0.000263
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
The warehouse was dim, lit only by a single flickering bulb that cast long shadows over Molly’s blueprints. She tapped the paper with a chewed pencil, her brow furrowed. Bill leaned over her shoulder, his breath reeking of stale coffee and regret. “We hit the party during the clown’s balloon animals,” Molly muttered. “Kids’ll be distracted, parents drunk on punch.” Bill scratched his stubble. “What if someone catches us?” Molly rolled her eyes. “We’re dressed as clowns, Bill. Nobody questions clowns.” A nearby rat scurried across the floor, as if mocking their plan. Bill adjusted his oversized rainbow wig, the synthetic fibers itching his scalp. Molly had already painted her face—wide grin, teardrop, the works. She looked unsettlingly cheerful. “You got the getaway bike?” she asked. Bill patted the rusty tricycle behind him. “Pink streamers included.” Molly sighed. “Perfect.” Outside, the distant sound of children’s laughter drifted in. Bill wiped his palms on his polka-dotted pants. Molly stuffed a sack with fake flowers—camouflage for the loot. “Last question,” Bill said. “What if the clown’s better than us?” Molly grinned. “Then we steal his nose too.”
created_at
"2026-02-16T21:33:59.324212+00:00"
2/16/2026, 9:33:59 PM
model
"deepseek/deepseek-chat-v3-0324"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1405
moderation_latency
(null)
generation_time
7847
tokens_prompt
77
tokens_completion
337
native_tokens_prompt
66
native_tokens_completion
283
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
0.000263296
router
(null)
provider_responses
0
status
(null)
is_byok
false
latency
5078
endpoint_id
"d562908f-c5eb-4a32-9a91-24d53b176fd8"
provider_name
"SiliconFlow"
model_permaslug
"deepseek/deepseek-chat-v3-0324"
1
id
"7f8275165b2246a29b3d6e8b9fc0107a"
status
200
is_byok
false
latency
1405
endpoint_id
"5bb598f5-fd97-4f8b-91e4-ceab3743a03b"
provider_name
"AtlasCloud"
model_permaslug
"deepseek/deepseek-chat-v3-0324"
api_type
"completions"
id
"gen-1771277625-BrXCBWB2NocYuPVOsHQi"
upstream_id
"7f8275165b2246a29b3d6e8b9fc0107a"
total_cost
0.000263296
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AtlasCloud"
Evaluation details
Result
Evaluator
Details
Meta Data
81.2727%
Matches word count
n/a
neededClean
false
words
188
0.0018%
Dialogue to Total Word Ratio
Ratio: 28.19%, Deviation: 18.19%
neededClean
false
wordsTotal
188
wordsDialogue
53
40.6372%