NC Bench
Overview
About
Tests
Models
Model
Llama 3.1 Nemotron 70B
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-10-16-01JABHY04YZRDBYN3ZJXMWHYV4
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 schematics of "Kiddie Kingdom" on the coffee table, her eyes scanning the layout of the children's play center. Bill lounged on the couch behind her, tossing a stress ball into the air. "Alright, here's the plan," Molly said, tapping a finger on the blueprint. "We sneak in during the Johnson kid's birthday party. Chaos, noise, perfect cover." "Genius," Bill said, catching the stress ball. "And our mark is...?" "All. The. Presents." Molly's grin gleamed mischievously. "I mean, who needs the Mona Lisa when you can swipe a haul of Tamagotchis and PlayStations?" "Priorities, Molly." Bill chuckled. "But how do we get past the parents? They'll be hovering like, well, parents." "We blend in. I've got a fantastic 'cool aunt' disguise – distressed denim, a fanny pack..." Molly struck a pose. Bill raised an eyebrow. "And I'll be...?" "Uncle Bill, the slightly-unsettling-but-probably-harmless guy who's 'helping out' with the bounce house."
id
"gen-1729112244-wKFesDYEt5KjUXsNa1zI"
upstream_id
"cmpl-Re5S5JRF9e6obQLflf1IVOz1"
total_cost
0.00012245
cache_discount
(null)
created_at
"2024-10-16T20:57:36.122737+00:00"
Wednesday, October 16th, 2024 at 8:57:36 PM GMT+00:00
model
"nvidia/llama-3.1-nemotron-70b-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"DeepInfra"
latency
70
moderation_latency
(null)
generation_time
10816
finish_reason
"stop"
tokens_prompt
102
tokens_completion
244
native_tokens_prompt
71
native_tokens_completion
244
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00012245
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
156
33.0689%
Dialogue to Total Word Ratio
Ratio: 60.26%, Deviation: 10.26%
neededClean
false
wordsTotal
156
wordsDialogue
94
16.5345%