NC Bench
Overview
About
Tests
Models
Model
Llama 3.1 70B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-23-01J3G806A1W1QACEH73R6M2BP2
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
"I'm telling you, Bill, this is a genius plan. Who expects thieves to hit a kiddie party?" Molly said, studying the blueprints of the community center. "Who indeed? But what's the haul? Plastic toys and rubber chickens?" Bill asked, raising an eyebrow. "Ah, but it's not just the toys, my friend. It's the art of the heist. We're not just thieves, we're performance artists," Molly replied, a mischievous grin spreading across her face. "Performance artists? You mean we're going to wear unitards and recite poetry while we make off with the good stuff?" Molly chuckled. "Well, maybe not poetry, but I did think of wearing a costume. A clown suit, perhaps?" Bill's face turned bright red. "You're out of your mind, Molly. I'm not wearing a clown suit. I'm a professional, not a children's party entertainer." "Come on, Bill, it'll be fun! We can make balloon animals while we work," Molly teased, winking at her partner. Bill shook his head. "You're enjoying this a little too much, Molly. What's the real plan?"
id
"gen-V2YkUunW4DcbP6fNjBP9UGW10392"
total_cost
0.0002871
upstream_id
"0ab82973-2dc3-4553-9fba-f2b316d03023"
created_at
"2024-07-23T16:50:13.616089+00:00"
Tuesday, July 23rd, 2024 at 4:50:13 PM GMT+00:00
model
"meta-llama/llama-3.1-70b-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"Fireworks"
latency
3227
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
102
tokens_completion
247
native_tokens_prompt
70
native_tokens_completion
249
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0002871
Evaluation details
Result
Evaluator
Details
Meta Data
0.2141%
Matches word count
n/a
neededClean
false
words
172
4.5610%
Dialogue to Total Word Ratio
Ratio: 76.74%, Deviation: 13.26%
neededClean
false
wordsTotal
172
wordsDialogue
132
2.3875%