NC Bench
Overview
About
Tests
Models
Model
Llama 3.2 1B
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-09-26-01J8PYX4ZYFB4KCJ3SBP48MC0R
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 and Bill huddled in the cramped alleyway, breathing heavily as they pored over the party plan. "We can use the fake mustache one," Molly whispered, displaying her hand with the absurd prop. "It's 90s kid culture chic." Bill raised an eyebrow. "I'll set off the sound effect. I'll give a booming 'Who's ready for snowball fight?' to really sell it." Molly grinned mischievously. "I'll sneak up and start tossing candy canes like a villain. The kids will be gagging." Bill chuckled. "Good, because that's exactly what they need. More gagging. I'll swing in and snatch as many presents as I can carry while the party hyped." Molly nodded. "Perfect. The best part is, the mom will be distracted by the 'special guest's' snowball fight. It'll be like Christmas just got a whole lot crazier." As they finished rehearsing, a knock at the door broke the silence. Molly's eyes gave Bill a pleading look. "Shh, do you hear that?"
id
"gen-WZHIHROu4v5iHVtSsgZLXOHab1pd"
total_cost
0.00003
upstream_id
"4ef5e06c-2ce2-47ac-8440-b7370d6ab742"
created_at
"2024-09-26T10:44:24.032774+00:00"
Thursday, September 26th, 2024 at 10:44:24 AM GMT+00:00
model
"meta-llama/llama-3.2-1b-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Fireworks"
latency
241
moderation_latency
(null)
generation_time
425
finish_reason
"stop"
tokens_prompt
102
tokens_completion
227
native_tokens_prompt
71
native_tokens_completion
229
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00003
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
159
0.8465%
Dialogue to Total Word Ratio
Ratio: 64.78%, Deviation: 14.78%
neededClean
false
wordsTotal
159
wordsDialogue
103
0.4233%