Nova Pro

Amazon Nova Pro is a cutting-edge multimodal model designed to handle text, image, and video inputs with advanced processing capabilities. Featuring a 300K-token context window, it excels in document analysis, visual question answering, and complex agent-driven workflows. As part of the Amazon Nova foundation models, it supports fine-tuning and distillation, enabling deep customization for various applications.

Llama 3.3 70B Instruct

Llama 3.3 70B Instruct, created by Meta, is a multilingual large language model specifically fine-tuned for instruction-based tasks and optimized for conversational applications. It is capable of processing and generating text in multiple languages, with a context window supporting up to 128,000 tokens. Launched on December 6, 2024, the model surpasses numerous open-source and proprietary chat models in various industry benchmarks. It utilizes Grouped-Query Attention (GQA) to improve scalability and has been trained on a diverse dataset comprising over 15 trillion tokens from publicly available sources. The model's knowledge is current up to December 2023.

Nova ProLlama 3.3 70B Instruct
Provider
Web Site
Release Date
Dec 02, 2024
4 months ago
Dec 06, 2024
4 months ago
Modalities
text ?
images ?
video ?
text ?
API Providers
Amazon Bedrock
Fireworks, Together, DeepInfra, Hyperbolic
Knowledge Cut-off Date
Purposefully not disclosed
12.2024
Open Source
No
Yes
Pricing Input
$0.80 per million tokens
$0.23 per million tokens
Pricing Output
$3.20 per million tokens
$0.40 per million tokens
MMLU
85.9%
CoT
Source
86%
0-shot, CoT
Source
MMLU Pro
Not available
68.9%
5-shot, CoT
Source
MMMU
Not available
Not available
HellaSwag
Not available
Not available
HumanEval
89%
pass@1
Source
88.4%
pass@1
Source
MATH
76.6%
CoT
Source
77%
0-shot, CoT
Source
GPQA
46.9%
Main
Source
50.5%
0-shot, CoT
Source
IFEval
92.1%
Source
92.1%
Source
Mobile Application
-
-

Compare LLMs

Add a Comment


10%
Our site uses cookies.

Privacy and Cookie Policy: This site uses cookies. By continuing to use the site, you agree to their use.