NC Bench
Overview
About
Tests
Models
Model
Llama 3.1 Nemotron 70B
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-10-16-01JABHZ4NPVXX1QEMJMTFZQZXW
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 pored over the blueprints of "Kiddie Kingdom" spread across their makeshift planning table, a worn Formica dinette set in Bill's cramped apartment. Bill, sipping on a lukewarm energy drink, rubbed the grit from his eyes. "Alright, so we've got the ingress covered – ventilation shaft in the ball pit," Molly said, tapping the diagram. "Sounds like a bad respiratory decision waiting to happen," Bill replied, "but I like it. What's the present-to-kid ratio looking like for this shindig?" "Estimated thirty kids, each averaging three gifts. That's ninety presents, Bill. We're talking upwards of five grand in potential loot." "Potential loot that's probably 90% plastic crap and 10% decent Lego sets," Bill said, raising an eyebrow. "You sure this is worth the risk of being trampled by sugar-high toddlers?" Molly grinned mischievously. "That's the best part – we're not just thieves, Bill. We're the ultimate party crashers."
id
"gen-1729112281-kg4uFKy1egPkafrnynG1"
upstream_id
"cmpl-RGlri2Y9CDszd56jLPviEYhB"
total_cost
0.00011165
cache_discount
(null)
created_at
"2024-10-16T20:58:09.29394+00:00"
Wednesday, October 16th, 2024 at 8:58:09 PM GMT+00:00
model
"nvidia/llama-3.1-nemotron-70b-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"DeepInfra"
latency
72
moderation_latency
(null)
generation_time
6860
finish_reason
"stop"
tokens_prompt
102
tokens_completion
217
native_tokens_prompt
71
native_tokens_completion
217
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00011165
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
148
0.0291%
Dialogue to Total Word Ratio
Ratio: 66.89%, Deviation: 16.89%
neededClean
false
wordsTotal
148
wordsDialogue
99
0.0146%