NC Bench
Overview
About
Tests
Models
Model
Llama 3.1 Nemotron 70B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-10-16-01JABHXMNZXJS2J1KSKSS3N516
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, Molly, this is the score of a lifetime. A room full of sugar-high kids, distracted parents... it's like they're begging us to steal the loot," Bill said, eyes shining with excitement. "Present loot, you mean. We're risking jail time for a bunch of teddy bears and playsets," Molly countered, scrutinizing the party venue's blueprints. "Hey, don't knock it till you see the guest list. The Smiths are invited – their kid always gets the latest gadgets. And the Joneses, they're rumored to have impeccable taste in action figures," Bill argued. "Impeccable taste in action figures? Who says that in a heist planning meeting?" Molly raised an eyebrow. "Someone who's done their research, that's who. Now, are we in or out? The cake's being delivered in an hour, and I have a cake-shaped diversion to attend to," Bill said, grinning mischievously. Molly sighed. "Fine, but if I get trampled by a pack of Kinder-Surprises-fueled zombies, I'm blaming you." "That's the spirit! Now, let's get to work – we have some presents to pilfer!"
id
"gen-1729112232-NtvQ9NImTRnIa7hK7uNx"
upstream_id
"cmpl-RcnMlPVXs9wCoES9ftLvVJBq"
total_cost
0.00012685
cache_discount
(null)
created_at
"2024-10-16T20:57:20.769401+00:00"
Wednesday, October 16th, 2024 at 8:57:20 PM GMT+00:00
model
"nvidia/llama-3.1-nemotron-70b-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"DeepInfra"
latency
73
moderation_latency
(null)
generation_time
7054
finish_reason
"stop"
tokens_prompt
102
tokens_completion
255
native_tokens_prompt
71
native_tokens_completion
255
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00012685
Evaluation details
Result
Evaluator
Details
Meta Data
6.0907%
Matches word count
n/a
neededClean
false
words
177
97.1481%
Dialogue to Total Word Ratio
Ratio: 85.88%, Deviation: 4.12%
neededClean
false
wordsTotal
177
wordsDialogue
152
51.6194%