NC Bench
Overview
About
Tests
Models
Model
Llama 3.1 Nemotron 70B
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2024-10-16-01JABHYRJ7CABBN0VKV36WYT9J
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 pored over the blueprint of "Kiddie Kingdom" party venue, a mischievous glint in her eye. Bill, lounging on the couch behind her, crunched on a potato chip, the sound amplifying in the tense silence. "Alright, here's the plan," Molly said, finally, her finger tracing the layout. "We hit the party during the pinata ceremony. Chaos will be our friend." Bill swallowed, his eyes lighting up. "I love chaos. What's the haul?" "All presents, plus the infamous 'Golden Cupcake' award – solid gold, Bill. Solid." Bill whistled, "Sweet. And how do we get past 'Bouncy Bob' and his vigilant gaze?" Molly smirked, "Leave that to me. I've got a disguise that'll make me blend in seamlessly with theWSJ-shortlisted-children's-party-entertainer crowd." Bill raised an eyebrow, "A clown suit?" Molly nodded, unfazed. "The ultimate travellers' cloak of invisibility. No one suspects a thing from a grown adult in a bright orange wig." Bill chuckled, the crunching resumed, "You're a genius, Molls."
id
"gen-1729112269-9z3h9HFMcWSveSnGEjGa"
upstream_id
"cmpl-REULwWRC6fIVMSgkXnkxib7L"
total_cost
0.00012485
cache_discount
(null)
created_at
"2024-10-16T20:58:03.175424+00:00"
Wednesday, October 16th, 2024 at 8:58:03 PM GMT+00:00
model
"nvidia/llama-3.1-nemotron-70b-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"DeepInfra"
latency
81
moderation_latency
(null)
generation_time
12860
finish_reason
"stop"
tokens_prompt
102
tokens_completion
250
native_tokens_prompt
71
native_tokens_completion
250
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00012485
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
161
0.0000%
Dialogue to Total Word Ratio
Ratio: 60.87%, Deviation: 50.87%
neededClean
false
wordsTotal
161
wordsDialogue
98
0.0000%