Model

Llama 3.1 70B

Test

Dialogue tags

Scenario

Write 200 words with 90% dialogue

Run ID

2024-07-23-01J3G80ZDG94T24JGAQ9JEZC60

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

AI
"I'm telling you, Bill, this is a goldmine. A bunch of sugar-high kids and their oblivious parents. We'll be in and out with the loot in no time." "What loot, exactly? A bunch of toy cars and stuffed animals? I'm a professional, Molly. I don't do birthdays." "Professional? You're a 40-year-old man who's been arrested for stealing a tub of margarine. I think you're the perfect guy for this job." "Hey, that margarine was a high-end, artisanal product. It was a challenge, okay?" "Whatever. The point is, these kids have been dropping hints for weeks. We're talking iPads, dollhouses, the works. And the parents are too busy Pinteresting their party decorations to notice us." "And what's the plan, genius? We just waltz in, grab the presents, and make a run for it?" "Well, when you put it that way, it sounds a little reckless. But trust me, I've got a plan. We'll dress up as clowns, create a diversion, and... Ah, come on, it'll be fun! You can't resist the allure of a good loot-and-sprint." "You know, sometimes I wonder how we're still friends."
id"gen-lWojaVxDhHnKWc3mveNoNGw0KuBg" 
total_cost0.0003024
upstream_id"a174e4d6-c9a9-4088-97e5-1825f1c30b88" 
created_at"2024-07-23T16:50:39.053881+00:00" Tuesday, July 23rd, 2024 at 4:50:39 PM GMT+00:00
model"meta-llama/llama-3.1-70b-instruct" 
app_id182717
streamedfalse
cancelledfalse
provider_name"Fireworks" 
latency3052
moderation_latency(null)
generation_time0
finish_reason"stop" 
tokens_prompt102
tokens_completion264
native_tokens_prompt70
native_tokens_completion266
num_media_prompt(null)
num_media_completion(null)
origin"https://ncbench.com/" 
usage0.0003024

Evaluation details

Result Evaluator Details Meta Data
90.4837% Matches word count n/a
neededCleanfalse
words190
36.7879% Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededCleanfalse
wordsTotal190
wordsDialogue190
63.6358%