NC Bench
Overview
About
Tests
Models
Model
Llama 3 70B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-19-01J35SWE02SVWWKC2V2TZNWSKP
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
"Alright, so we're clear on the plan, right? We hit the party at two, when all the sugar-high kids are distracted by the clown?" "Clown? You think they're gonna have a clown? That's just mean." "Mean? It's a kid's party, Bill. They're gonna have a clown. Anyway, once the clown's got their attention, we slip in, grab the gifts, and slip out." "And what's the signal to get out?" "When you hear the words 'cake time', we're gone. No one sticks around for cake." "I don't know, Moll. This feels wrong. We're stealing from kids." "Come on, they're not gonna miss a few toys. Besides, we're giving them a story to tell. 'Hey, remember that time the presents got stolen at my birthday party?' It's character building." "But what about the parents? They're gonna freak." "Let them freak. We'll be long gone, sipping margaritas on a beach somewhere, surrounded by Fisher-Price loot." "Fine, but if we get caught, I'm blaming the clown."
id
"gen-p1rxodCpdueF2qXOhVcaFIFdKFVN"
total_cost
0.00023562
upstream_id
"cmpl-9fded62c6cd745a78c78fefc6b8aa33e"
created_at
"2024-07-19T15:31:06.497342+00:00"
Friday, July 19th, 2024 at 3:31:06 PM GMT+00:00
model
"meta-llama/llama-3-70b-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"OctoAI"
latency
3876
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
102
tokens_completion
236
native_tokens_prompt
72
native_tokens_completion
236
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00023562
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
164
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
164
wordsDialogue
164
18.3940%