NC Bench
Overview
About
Tests
Models
Model
Llama 3.2 1B
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2024-09-26-01J8PZ49V85SYXK1KC90PA2XH8
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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
Molly adjusted her thick-rimmed glasses and gave Bill a sly grin. They stood in the dimly lit alley, their eyes locked on the nondescript package wrapped in brown paper and twine, left on the ground amidst the scattered trash. The party organizers, still reeling from their own scheme, had forgotten them. The prize? All the presents. A haul they could hardly believe. "Are you sure this is a good idea?" Molly asked, their voice barely above a whisper. Bill shrugged, shouldering the case. "The kid who did this is a bit too enthused. We don't want him to know where we were exactly." Molly snorted. "And who's to say there isn't a security camera. We'll get caught by the parents. I've got a great idea for a heist...like a 're-decorate' heist." Bill raised an eyebrow. "A 're-decorate' heist? You know I like the original plan." Molly just smiled confidently. "That's what makes it more fun. Now, come on. We've got a job to get to."
id
"gen-rUo6KKPqmDdF9TUKPsjjbaehwQJn"
total_cost
0.0000308
upstream_id
"6f61d9f5-9245-40a2-8aed-4d49c5e74663"
created_at
"2024-09-26T10:48:18.2952+00:00"
Thursday, September 26th, 2024 at 10:48:18 AM GMT+00:00
model
"meta-llama/llama-3.2-1b-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Fireworks"
latency
125
moderation_latency
(null)
generation_time
461
finish_reason
"stop"
tokens_prompt
102
tokens_completion
236
native_tokens_prompt
71
native_tokens_completion
237
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0000308
Evaluation details
Result
Evaluator
Details
Meta Data
0.0028%
Matches word count
n/a
neededClean
false
words
168
0.0000%
Dialogue to Total Word Ratio
Ratio: 48.81%, Deviation: 38.81%
neededClean
false
wordsTotal
168
wordsDialogue
82
0.0014%