NC Bench
Overview
About
Tests
Models
Model
Llama 3.1 405B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-23-01J3G5110NKQJRQ8PCB05CY77N
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 rummaged through the brochures on her kitchen counter, stopping at the one with the cartoon clown on the front. "Kiddie Palooza, the most epic children's party of the year. This is it, Bill. The mother lode of presents." Bill leaned back in his chair, sipping his coffee. "You want to steal from kids?" "Not from the kids, from the parents," Molly corrected. "Those guys are made of money. Designer toys, gadgets, and cash. We can make a killing." "Assuming we don't get caught by a pack of sugar-high six-year-olds," Bill said dryly. "We'll be in and out, like pros. Besides, who's going to suspect a thing? 'Hey, where's Timmy's expensive robot dog?' 'Oh, he must have left it at home...or it was stolen by skilled thieves.'" Bill raised an eyebrow. "You've really thought this through, haven't you?" Molly grinned mischievously. "I've been casing this party for weeks. I know the layout, the schedule, the snack table. We'll blend right in with the hired entertainment." "And what's our supposed act?" "I was thinking we could be... balloon animal specialists."
id
"gen-mrAll6libVynyjdfKd1EgTdTmSoQ"
total_cost
0.000999
upstream_id
"08cca27d-d9b7-4704-b1b0-e1f9d2d5574f"
created_at
"2024-07-23T15:58:22.891837+00:00"
Tuesday, July 23rd, 2024 at 3:58:22 PM GMT+00:00
model
"meta-llama/llama-3.1-405b-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"Fireworks"
latency
11128
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
102
tokens_completion
261
native_tokens_prompt
70
native_tokens_completion
263
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.000999
Evaluation details
Result
Evaluator
Details
Meta Data
35.0022%
Matches word count
n/a
neededClean
false
words
182
8.5184%
Dialogue to Total Word Ratio
Ratio: 77.47%, Deviation: 12.53%
neededClean
false
wordsTotal
182
wordsDialogue
141
21.7603%