NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHM5E2K3Z4B6W2QTP58NM1HX
Run Details
Model:
DeepSeek V3 (2025-03-24)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
8.2s
Cost:
$0.000307
Provider:
SiliconFlow
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 dim glow of a flickering streetlight cast long shadows across the rickety table in Molly and Bill’s hideout—a rundown apartment above a defunct pet store. Spread between them was a hand-drawn map of the neighborhood, with a circle around the Thompson residence. Molly tapped the paper with a chewed pencil. “Kid’s birthday party starts at noon, which means presents will be piled high by 12:05. Distraction’s key—I’ll dress as a clown.” Bill scoffed. “You? A clown? Last time you wore face paint, you scared a nun.” “Fine, you handle the disguise.” Molly crossed her arms. “But we need a clean getaway. I checked—Thompson’s got a dog. A Yorkie.” Bill grinned. “Piece of cake. I’ll bring bacon. Dogs love bacon.” Molly rolled her eyes. “And what if the parents notice two grown adults sneaking off with a sack of toys?” Bill shrugged. “We say we’re the entertainment. Who questions a magician?” Molly paused. “Alright. But if we get caught, I’m blaming the clown.” Bill saluted. “Deal. Now, let’s rehearse the escape plan… or do you wanna wing it?” Molly groaned. “We’re doomed.”
created_at
"2026-02-16T21:24:29.151824+00:00"
2/16/2026, 9:24:29 PM
model
"deepseek/deepseek-chat-v3-0324"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1151
moderation_latency
(null)
generation_time
8074
tokens_prompt
77
tokens_completion
317
native_tokens_prompt
66
native_tokens_completion
290
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
0.0003065
router
(null)
provider_responses
0
id
"019c68570b303a0be172f61b175e2d3d"
status
200
is_byok
false
latency
1151
endpoint_id
"d562908f-c5eb-4a32-9a91-24d53b176fd8"
provider_name
"SiliconFlow"
model_permaslug
"deepseek/deepseek-chat-v3-0324"
api_type
"completions"
id
"gen-1771277060-gnj8G8GTcaboJGt7BGq9"
upstream_id
"019c68570b303a0be172f61b175e2d3d"
total_cost
0.0003065
cache_discount
(null)
upstream_inference_cost
0
provider_name
"SiliconFlow"
Evaluation details
Result
Evaluator
Details
Meta Data
68.1022%
Matches word count
n/a
neededClean
false
words
186
26.2683%
Dialogue to Total Word Ratio
Ratio: 60.75%, Deviation: 10.75%
neededClean
false
wordsTotal
186
wordsDialogue
113
47.1853%