NC Bench
Overview
About
Tests
Models
Model
Llama 3.1 Nemotron 70B
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-10-16-01JABHYBBE94VZBWZTEP0PBWSV
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 spread out the blueprint of "Pony Palace" on the cluttered kitchen table, Bill leaning in beside her, a bowl of stale cereal between them. The venue was notorious for its extravagant children's parties. "Alright, so we've got three entrances, two emergency exits, and a ball pit that's just begging to swallow a thief whole," Molly said, tracing the layout with her finger. "I'm more concerned about the potential for sugar highs and water balloon ambushes," Bill replied, crunching on a cereal flake. Molly chuckled. "You worry too much. We're in, we snatch the presents, we're out. It's not like we're stealing the Mona Lisa... just a bunch of overpriced plastic toys." "Tell that to the toddler who just lost their ' copyrighted, limited-edition, Sparkles McGee doll'," Bill said, raising an eyebrow. "Sparkles McGee is going to fund our retirement, Bill. Now, who takes the gift table and who distracts the adults with the fake piƱata emergency?"
id
"gen-1729112255-f5bDIBe8yJV7d3erfHbQ"
upstream_id
"cmpl-RCgm8w5LRZYkslsZsZ0fj0zh"
total_cost
0.00011205
cache_discount
(null)
created_at
"2024-10-16T20:57:43.248314+00:00"
Wednesday, October 16th, 2024 at 8:57:43 PM GMT+00:00
model
"nvidia/llama-3.1-nemotron-70b-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"DeepInfra"
latency
63
moderation_latency
(null)
generation_time
6752
finish_reason
"stop"
tokens_prompt
102
tokens_completion
218
native_tokens_prompt
71
native_tokens_completion
218
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00011205
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
157
0.2658%
Dialogue to Total Word Ratio
Ratio: 65.61%, Deviation: 15.61%
neededClean
false
wordsTotal
157
wordsDialogue
103
0.1329%