NC Bench
Overview
About
Tests
Models
Model
Llama 3.2 3B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-09-26-01J8PZ0E0KYNCJ44KHPYAEQ9CH
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 don't know, Bill. This is a bad idea. Oh wait, that's my job description, I forget sometimes." "Six years of experience, Molly. We've sniffed out more valuable loot in a kindergarten than at any actual kid's museum." "Exactly that's why I'm saying it's a bad idea. Kids are like random wild cards. What if we get shot with a Nerf gun?" "We'll wear our 'I'm a crazy cat lady' disguises. Nothing says 'bad guy' like a violin playing granny." "You really think those Tracking Pants will hold up to a high-five from a sugar-fueled five-year-old?" "It's not just any high-five, Molly. It's a high-five with a tantrum that may or may not involve hitting the adult in charge with a juice box." "If we get caught, do we just claim we're talented street performers or do we go with the ' America's Funniest Home Videos' routine?" "Either way, I'm not going to Oops-a-Daisy an elephant-ear printer with our getaway van." "Exactly why you get to be the getaway driver, it's a safety hazard waiting to happen."
id
"gen-sb1clnTS9ZS73ZAh72DxTVtttcEz"
total_cost
0.00001701
upstream_id
"8c92ab2d54a92544-SJC"
created_at
"2024-09-26T10:46:35.462108+00:00"
Thursday, September 26th, 2024 at 10:46:35 AM GMT+00:00
model
"meta-llama/llama-3.2-3b-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Together"
latency
22887
moderation_latency
(null)
generation_time
1633
finish_reason
"eos"
tokens_prompt
102
tokens_completion
243
native_tokens_prompt
71
native_tokens_completion
244
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00001701
Evaluation details
Result
Evaluator
Details
Meta Data
60.2752%
Matches word count
n/a
neededClean
false
words
185
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
185
wordsDialogue
185
48.5316%