NC Bench
Overview
About
Tests
Models
Model
Llama 3.2 1B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-09-26-01J8PZ11CCQMEQCP6X31THJDVP
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've always wanted to put 'Kid-Napping for Beginners' to use for my next heist." "Just because it's not as boring as 'Flight Risk' doesn't mean I'm not in the mood for something family-friendly, Molly." "Hey, don't get ahead of yourself Bill. We have to be stealthy. We can't risk getting caught in the attic." "The attic, schmatte. We're not doing the attic part. The big check, the getaway limo, the mint-condition teddy bear I bought online last year... I want it all." "Dude, I don't know why we're even doing this. We could just buy those things online like normal people." "Of course we could, but where's the spice of life?" We're making a statement. We're defying the patriarchy. Now, let's review the security cameras. What do we have? Ah, two cameras in the corner, one on the top of the treehouse... and a security guard who looks like his aunt." "Bingo. What's the plan now?"
id
"gen-6bxPivUzN9eZwrT4D00oVqPOKnd2"
total_cost
0.0000294
upstream_id
"ea924c19-5163-4a87-8665-c64ae192137f"
created_at
"2024-09-26T10:46:31.376709+00:00"
Thursday, September 26th, 2024 at 10:46:31 AM GMT+00:00
model
"meta-llama/llama-3.2-1b-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Fireworks"
latency
140
moderation_latency
(null)
generation_time
432
finish_reason
"stop"
tokens_prompt
102
tokens_completion
221
native_tokens_prompt
71
native_tokens_completion
223
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0000294
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
159
0.0703%
Dialogue to Total Word Ratio
Ratio: 73.58%, Deviation: 16.42%
neededClean
false
wordsTotal
159
wordsDialogue
117
0.0351%