NC Bench
Overview
About
Tests
Models
Model
Llama 3.1 405B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-23-01J3G511DBAQ9TZ03E72MEVBGG
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 going to be a cakewalk," Molly said, studying the layout of the children's party venue. "A cakewalk? Are you insane? We're going to steal presents from a bunch of sugared-up toddlers. This is a recipe for disaster," Bill replied, adjusting his ski mask. "Come on, it'll be fun. We can dress up as clowns and no one will suspect a thing." "I hate clowns, Molly. And what's with the get-rich-quick scheme? Can't we just stick to the usual jewelry heists?" "Presents, Bill. Expensive, brand-new, still-in-the-box presents. We can fence them online for a small fortune. Plus, who doesn't want to ruin a bunch of kids' birthday party?" "That's just it. I don't want to ruin a bunch of kids' birthday party. I have a niece, Molly. I know how much these things mean to them." "Sentimental sap. Fine, I'll give you a bigger cut if you just put on the stupid clown nose and let's get this over with." "Seventy-thirty, or I walk." "Sixty-forty, and that's my final offer."
id
"gen-caYd9OCoiy9O9D3hVMjO8Me43mfu"
total_cost
0.000999
upstream_id
"1d8b98d0-72fe-485d-842e-2a9f40ff71af"
created_at
"2024-07-23T15:58:23.396687+00:00"
Tuesday, July 23rd, 2024 at 3:58:23 PM GMT+00:00
model
"meta-llama/llama-3.1-405b-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"Fireworks"
latency
11207
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
51.9255%
Matches word count
n/a
neededClean
false
words
184
99.9711%
Dialogue to Total Word Ratio
Ratio: 91.30%, Deviation: 1.30%
neededClean
false
wordsTotal
184
wordsDialogue
168
75.9483%