Model

Llama 3.1 70B

Test

Dialogue tags

Scenario

Write 200 words with 90% dialogue

Run ID

2024-07-23-01J3G80KGQM95TZS5FY1VH3M7Y

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 solid plan. A kids' party, no security to speak of, and a room full of sugar-high obliviousness." "Obviousness, not obliviousness, Molly. And I'm not sure I'm comfortable with this. It's a bunch of kids' birthday presents. It's not exactly the score of a lifetime." "Come on, it's a score, nonetheless. And have you seen the sizes of those gift boxes? Those kids are probably getting iPads and bicycles. We can make a killing on eBay." "But what if we get caught? I don't want to spend my twenty-fifth birthday in a kiddie cellblock." "We won't get caught. We'll be in and out in ten minutes. I've got a disguise for us – who's going to suspect the piñata and the clown?" "Aren't you the one who always says, 'Don't dress as a clown, you're just asking for trouble'?" "Desperate times, Bill. Desperate times. Besides, I've got a great idea for a squirt gun and a whoopee cushion." "You're not taking this seriously, are you?" "I'm taking it very seriously. I'm taking thirty-five percent of the profits, and you're getting the rest. Now, are you in or out?"
id"gen-chB8paFzGISv7ktcmBKxLclBjMud" 
total_cost0.0003132
upstream_id"5aae525c-bc1e-4c74-bd2c-639780c1f1e6" 
created_at"2024-07-23T16:50:26.95566+00:00" Tuesday, July 23rd, 2024 at 4:50:26 PM GMT+00:00
model"meta-llama/llama-3.1-70b-instruct" 
app_id182717
streamedfalse
cancelledfalse
provider_name"Fireworks" 
latency3103
moderation_latency(null)
generation_time0
finish_reason"stop" 
tokens_prompt102
tokens_completion276
native_tokens_prompt70
native_tokens_completion278
num_media_prompt(null)
num_media_completion(null)
origin"https://ncbench.com/" 
usage0.0003132

Evaluation details

Result Evaluator Details Meta Data
99.7443% Matches word count n/a
neededCleanfalse
words196
36.7879% Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededCleanfalse
wordsTotal196
wordsDialogue196
68.2661%