NC Bench
Overview
About
Tests
Models
Model
Llama 3.1 8B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-23-01J3G80TNAHCBFBV2NK1GD19DN
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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 leaned back in her chair, a sly grin spreading across her face as she surveyed the layout of the party venue on the blueprints laid out before them. "Okay, here's the plan," Bill said, his eyes scanning the diagrams. "We hit the party at 3 PM, when all the kids are in the backyard getting their faces painted. The guests of honor are in their piƱata-filled glory, completely oblivious to the heist unfolding mere feet away." Molly snorted. "This is going to be too easy. I mean, who needs actual security when you've got a bunch of sugared-up five-year-olds?" "Exactly! And with that many presents under the tree, we're talking serious cash in the bank," Bill replied, his eyes shining with excitement. Molly rubbed her hands together. "I'm talking new handbags, Bill. Designer, leather, the works." Bill cleared his throat. "Uh, let's focus. We need to get in, grab the loot, and get out without setting off the security cameras." "Oh, don't worry, I've got those disabled," Molly said, her voice dripping with confidence. "I've been practicing my 'I'm a bored aunt' face. Nobody suspects a thing." Bill chuckled. "You're a genius, Molly. I'm hanging you out as the face of the operation."
id
"gen-fCWT7GhCuQeek9blGBeMbcWvwdLa"
total_cost
0.0000708
upstream_id
"c627ae45-4ab2-49af-99ee-0bac68403f6e"
created_at
"2024-07-23T16:50:32.194831+00:00"
Tuesday, July 23rd, 2024 at 4:50:32 PM GMT+00:00
model
"meta-llama/llama-3.1-8b-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"Fireworks"
latency
1092
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
102
tokens_completion
283
native_tokens_prompt
70
native_tokens_completion
284
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0000708
Evaluation details
Result
Evaluator
Details
Meta Data
95.9868%
Matches word count
n/a
neededClean
false
words
208
0.0000%
Dialogue to Total Word Ratio
Ratio: 69.71%, Deviation: 20.29%
neededClean
false
wordsTotal
208
wordsDialogue
145
47.9934%