NC Bench
Overview
About
Tests
Models
Model
Llama 3.1 8B
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-07-23-01J3G819X33G4EQ0A9QRS6RAZK
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 balloons were tied to the chairs, the sugary sweet aroma of cupcakes wafted through the air, and the kids were completely entranced by the piñata-swinging clown. Molly and Bill crouched behind a row of birthday banners, dressed in matching "I'm a superhero" t-shirts. "Not exactly the low-security target I was hoping for," Bill said, his voice hushed. "What's wrong, Bill? You scared of a few screaming children?" Molly shot back. "No, but what if we get caught in a sea of sparkly ponchos?" "Hey, people in ponchos can be ferocious," Molly deadpanned. Bill snorted. "You're not going to entertain yourself by making poncho puns all night, are you?" Molly held up her tablet, glowing with schematics of the party. "We have a plan. We go in during the cake-eating portion of the party – least distracted crowd." "The clown's still got their attention," Bill observed. "He's just getting started. That guy's a pro," Molly muttered. Bill's eyes flicked to the group of sugar-fueled four-year-olds, high on excitement and sugar. "We're really doing this, aren't we?" Molly flashed a sly grin. "Who's stopping us?" The clown wailed as he missed another piñata swing – perfect timing.
id
"gen-npQ9rZjuyE2y3VRLmzs7nSJpAcc0"
total_cost
0.0000716
upstream_id
"66218554-f74b-4675-8854-7ba001aa8568"
created_at
"2024-07-23T16:50:48.06699+00:00"
Tuesday, July 23rd, 2024 at 4:50:48 PM GMT+00:00
model
"meta-llama/llama-3.1-8b-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"Fireworks"
latency
1263
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
102
tokens_completion
287
native_tokens_prompt
70
native_tokens_completion
288
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0000716
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Matches word count
n/a
neededClean
false
words
200
99.9900%
Dialogue to Total Word Ratio
Ratio: 49.00%, Deviation: 1.00%
neededClean
false
wordsTotal
200
wordsDialogue
98
99.9950%