NC Bench
Overview
About
Tests
Models
Model
Llama 3.2 3B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-09-26-01J8PZ1FDDA1ENKF28A7G548V5
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 the score of a lifetime," Molly said, her eyes shining with excitement. "Ah, come on, Molly, it's a kid's birthday party. They're just gonna be playing with pinata and eating cake." "P presented? This is the mother lode," Molly replied. "All those presents, just chillin' on a table, waiting for us to swoop in and snatch 'em. I can see the cash register ringin' up by now." "You're not actually thinking of stealing a pinata, are you?" Bill asked, incredulous. "Well, yeah. That's where the cash is, Bill. Who takes down a clown?" Molly raised an eyebrow. "Cops? No, they'll be too busy chasing after rubber chickens. I'm talking seasoned pros." "Seasoned? You've been practicing your pinata- stealing skills in the mirror for three hours, Molly." "Hey, it's all about finesse. I'm like a ninja in a party hat. Okay, maybe not, but I've got a plan. We hit, we grab, we're out. It's a thing of beauty." Bill shook his head. "You're impossible."
id
"gen-2847fmaV7U6Tts3sGEOUngIYfqYC"
total_cost
0.000017496
upstream_id
"8c92ac03a137945c-SJC"
created_at
"2024-09-26T10:46:47.142896+00:00"
Thursday, September 26th, 2024 at 10:46:47 AM GMT+00:00
model
"meta-llama/llama-3.2-3b-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Together"
latency
137
moderation_latency
(null)
generation_time
1763
finish_reason
"eos"
tokens_prompt
102
tokens_completion
252
native_tokens_prompt
71
native_tokens_completion
253
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.000017496
Evaluation details
Result
Evaluator
Details
Meta Data
0.0304%
Matches word count
n/a
neededClean
false
words
170
99.9031%
Dialogue to Total Word Ratio
Ratio: 88.24%, Deviation: 1.76%
neededClean
false
wordsTotal
170
wordsDialogue
150
49.9667%