NC Bench
Overview
About
Tests
Models
Model
Llama 3.1 Nemotron 70B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-10-16-01JABHZ9FAYCB1RG75WB9MTC3K
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 genius. A kids' birthday party? The take is going to be all sugar-fueled chaos," Molly said, eyes scanning the party venue's layout on her laptop. "Chaos is right. Have you seen the guest list? Thirty five-year-olds on a bouncy castle? It's a war zone," Bill replied, rubbing his temples. "Exactly! They'll be too distracted to notice us swapping the presents with our fake, empty boxes. We'll be in and out in ten," Molly said, grinning. "Fake boxes? You really think the parents won't notice when little Timmy unwraps a cardboard box with 'TRUST US, IT'S FUN' scribbled on it?" "Details, Bill! We'll get some silly stickers, it'll be fine. Now, who's taking the pinata and who's on gift table duty?" "I'll take the pinata, but only if I get to hit it with a baseball bat. This job's going to require some stress relief." "Oh, you can smash all you want, just don't get too carried away – we need to blend in with the soccer moms."
id
"gen-1729112286-NhIjFyjbsiQ4FKgvWcvb"
upstream_id
"cmpl-RZpSy9oC1fECO2QW0BWktQaU"
total_cost
0.00012245
cache_discount
(null)
created_at
"2024-10-16T20:58:14.965499+00:00"
Wednesday, October 16th, 2024 at 8:58:14 PM GMT+00:00
model
"nvidia/llama-3.1-nemotron-70b-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"DeepInfra"
latency
67
moderation_latency
(null)
generation_time
7703
finish_reason
"stop"
tokens_prompt
102
tokens_completion
244
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
0.00012245
Evaluation details
Result
Evaluator
Details
Meta Data
2.0116%
Matches word count
n/a
neededClean
false
words
175
99.9946%
Dialogue to Total Word Ratio
Ratio: 89.14%, Deviation: 0.86%
neededClean
false
wordsTotal
175
wordsDialogue
156
51.0031%