NC Bench
Overview
About
Tests
Models
Model
Llama 3.1 Nemotron 70B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-10-16-01JABHZ1H5NR4YG0M0TJDWR33F
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, 'Princess Sparkles' themed parties are the new goldmine," Molly said, eyes fixed on the colorful flyer. "Are you insane? We're planning to rob a kids' birthday bash," Bill whispered, glancing around the cramped café. "Ah, come on! It's not like we're swiping their lunch money. These presents are top-shelf, overpriced junk. The parents will just write it off as a tax deduction." "Top-shelf junk? You've been watching too much QVC. What's the take, really?" "Conservative estimate? Five grand in toys, plus whatever cash the desperate parents stuffed into those tacky cards. And let's not forget the pièce de résistance: the bouncy castle rental money." Bill rubbed his temples. "You know the security, right? A harried events coordinator and a handful of sugar-high 7-year-olds?" Molly grinned mischievously. "That's not security, Bill – that's a welcome mat. Now, who's going to dress up as the entertainment?" "Ugh, not me. I draw the line at wearing a furry onesie." "Oh, don't be such a party pooper! You'll make a great 'Mr. Sparklepaws'!"
id
"gen-1729112278-Z1WRpoqAhMLbt7RpStOe"
upstream_id
"cmpl-RAuFHRLcIpWdkSZxTbh771WS"
total_cost
0.00013205
cache_discount
(null)
created_at
"2024-10-16T20:58:07.24933+00:00"
Wednesday, October 16th, 2024 at 8:58:07 PM GMT+00:00
model
"nvidia/llama-3.1-nemotron-70b-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"DeepInfra"
latency
242
moderation_latency
(null)
generation_time
7948
finish_reason
"stop"
tokens_prompt
102
tokens_completion
268
native_tokens_prompt
71
native_tokens_completion
268
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00013205
Evaluation details
Result
Evaluator
Details
Meta Data
2.0116%
Matches word count
n/a
neededClean
false
words
175
99.5637%
Dialogue to Total Word Ratio
Ratio: 87.43%, Deviation: 2.57%
neededClean
false
wordsTotal
175
wordsDialogue
153
50.7877%