NC Bench
Overview
About
Tests
Models
Model
Llama 3 70B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-19-01J35SXBYGS05Z77KK5V7F0MV0
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
"I'm telling you, Bill, this is genius. A children's birthday party? No one expects to get robbed at a bouncy castle." "Unless they're expecting a piñata heist, Molly. Have you considered the piñata variable?" "There is no piñata variable. It's a three-tiered cake, not a candy-filled donkey." "What if the kids get upset when we start swiping their gifts?" "Kids cry, Bill. It's what they do. We'll just blend in, wear some brightly colored wigs, and claim we're character actors." "Character actors with pillowcases full of loot?" "Details, Bill. We'll work out the details. Now, what's the layout of the party room?" "I've got blueprints, Molly. We've got a ball pit, a photo booth, and a ' Pin the Tail on the Donkey' station." "Perfect. We'll create a diversion at the donkey and make our move during the cake song." "You're assuming the kids can sing in harmony, Molly." "Oh, please. They're children. They can barely blow out candles without setting off the fire alarm."
id
"gen-ZEcL8noxzlucyb7rDsH6TwCs3RAK"
total_cost
0.00023868
upstream_id
"cmpl-e5e89efcace145359dcfd86ea8bded9b"
created_at
"2024-07-19T15:31:36.619336+00:00"
Friday, July 19th, 2024 at 3:31:36 PM GMT+00:00
model
"meta-llama/llama-3-70b-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"OctoAI"
latency
3397
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
102
tokens_completion
240
native_tokens_prompt
72
native_tokens_completion
240
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00023868
Evaluation details
Result
Evaluator
Details
Meta Data
0.0002%
Matches word count
n/a
neededClean
false
words
166
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
166
wordsDialogue
166
18.3941%