NC Bench
Overview
About
Tests
Models
Model
DeepSeek-V2 Chat
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2024-07-19-01J35SVWFQ178XTCFR3D3BDBG2
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 tapped her pen against the blueprint of the community center. "Alright, Bill, we hit the party at 7 PM sharp. The kids will be too busy with the magician to notice us." Bill, chewing on a stale pretzel, squinted at the map. "Magician, huh? Any chance he's in on it?" "Nope, straight up prestidigitation. We slip in, grab the gifts, and out before the rabbit gets suspicious." "What about the clowns?" Bill asked, his voice tinged with genuine concern. "Clowns are harmless. Besides, they'll be too busy trying to figure out how to drive that tiny car." Bill chuckled, then sobered. "And the parents?" "Parents are always glued to their phones. We'll be ghosts." "Ghosts with loot," Bill corrected, grinning. Molly nodded, her eyes gleaming. "Exactly. Ghosts with loot. Now, let's go over the escape route one more time." They bent their heads together, the plan unfolding like a well-rehearsed play. The community center, with its cacophony of laughter and magic, would soon be their stage.
id
"gen-yHqk96anx5gmoCeGdKdfKGUQcDaI"
total_cost
0.00008498
upstream_id
"1c48867894c73d7a946819e93795cb06"
created_at
"2024-07-19T15:31:00.302009+00:00"
Friday, July 19th, 2024 at 3:31:00 PM GMT+00:00
model
"deepseek/deepseek-chat"
app_id
182717
streamed
false
cancelled
false
provider_name
"DeepSeek"
latency
15665
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
242
native_tokens_prompt
73
native_tokens_completion
267
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00008498
Evaluation details
Result
Evaluator
Details
Meta Data
0.0028%
Matches word count
n/a
neededClean
false
words
168
0.0000%
Dialogue to Total Word Ratio
Ratio: 58.93%, Deviation: 48.93%
neededClean
false
wordsTotal
168
wordsDialogue
99
0.0014%