NC Bench
Overview
About
Tests
Models
Model
Llama 3.1 Nemotron 70B
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2024-10-16-01JABHZWM3147610X7NBBBN4T3
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 sprawled across the cramped, cluttered floor of their safehouse, a mess of scribbled notes, empty pizza boxes, and crumpled maps surrounding her. Bill leaned against the worn couch, eyes fixed on the grainy security footage playing on the laptop perched on a stack of old DVDs. The soundtrack of screaming children and off-key birthday songs filled the air. "Alright, so we've got two cameras, one guard who looks like he'd rather be anywhere else, and a guest list that reads like a diaper manufacturer's dream," Molly summarized, twirling a pen around her finger. Bill grunted, not looking up. "Presents are the real prize. I'm talking triple-digit gift cards, the latest toys... we could fence this haul for a small fortune." Molly's eyes sparkled with mischief. "I'm more excited about the cake. I mean, who doesn't love a good smash-and-grab with frosting on top?" Bill raised an eyebrow, a hint of a smile on his lips. "You're a weird thief, Molly."
id
"gen-1729112306-JOoGCClVAPU5ziz717qo"
upstream_id
"cmpl-R8b1YKKjTsNiWgUzDlkt2Ckg"
total_cost
0.00011325
cache_discount
(null)
created_at
"2024-10-16T20:58:33.298725+00:00"
Wednesday, October 16th, 2024 at 8:58:33 PM GMT+00:00
model
"nvidia/llama-3.1-nemotron-70b-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"DeepInfra"
latency
74
moderation_latency
(null)
generation_time
6207
finish_reason
"stop"
tokens_prompt
102
tokens_completion
221
native_tokens_prompt
71
native_tokens_completion
221
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00011325
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
165
0.0000%
Dialogue to Total Word Ratio
Ratio: 45.45%, Deviation: 35.45%
neededClean
false
wordsTotal
165
wordsDialogue
75
0.0000%