NC Bench
Overview
About
Tests
Models
Model
Llama 3.1 405B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-23-01J3G518RF7FGFNV6ZYH8P1CYP
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 adjusted the wig on her head, a frizzy blonde monstrosity that made her look like a failed 80s pop star. Bill snorted, nearly spitting out his coffee. "What's with the getup?" he asked, eyeing the rest of her outfit, a glittery pink sweat suit with cartoon characters emblazoned on it. "I'm going as a kids' party entertainer," Molly explained. "I figure it's the best way to blend in. You're the bouncy castle guy, remember?" Bill raised an eyebrow. "I'm more of a 'stand around and look menacing' kind of guy." Molly chuckled. "That's exactly why you're the bouncy castle guy. No one suspects the bouncy castle guy of being a thief. Now, let's go over the plan one more time." "Okay, so we sneak in through the back door, you create a diversion with the ball pit, and I swipe the presents," Bill recited, a bored look on his face. "Exactly. And then we meet back at the van and make our escape," Molly finished. "And what's the haul looking like?" Bill asked, a hint of excitement creeping into his voice. "From what I've gathered, this party's got some serious money behind it. We're talking top-of-the-line toys, Electronics, maybe even some cash gifts. We could make a pretty penny," Molly said with a grin. Bill whistled low. "Not bad for a kids' party."
id
"gen-miX9qwGr1ouEeVccc7HzxiyvvFYD"
total_cost
0.001158
upstream_id
"a91cdbf2-c3b2-40c7-8865-9a80dd4ee39f"
created_at
"2024-07-23T15:58:35.83437+00:00"
Tuesday, July 23rd, 2024 at 3:58:35 PM GMT+00:00
model
"meta-llama/llama-3.1-405b-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"Fireworks"
latency
16078
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
102
tokens_completion
314
native_tokens_prompt
70
native_tokens_completion
316
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.001158
Evaluation details
Result
Evaluator
Details
Meta Data
0.4920%
Matches word count
n/a
neededClean
false
words
227
0.0000%
Dialogue to Total Word Ratio
Ratio: 63.44%, Deviation: 26.56%
neededClean
false
wordsTotal
227
wordsDialogue
144
0.2460%