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.
| Claude Sonnet 4 | Llama 3.3 70B Instruct | |
|---|---|---|
Provider | ||
Web Site | ||
Release Date | May 22, 2025 3 days ago | Dec 06, 2024 5 months ago |
Modalities | text images | text |
API Providers | Anthropic API, Amazon Bedrock, Google Cloud's Vertex AI | Fireworks, Together, DeepInfra, Hyperbolic |
Knowledge Cut-off Date | Unknown | 12.2024 |
Open Source | No | Yes |
Pricing Input | $3 per million tokens | $0.23 per million tokens |
Pricing Output | $15 per million tokens | $0.40 per million tokens |
MMLU | 86.5% Source | 86% 0-shot, CoT Source |
MMLU Pro | - | 68.9% 5-shot, CoT Source |
MMMU | 74.4% Source | Not available |
HellaSwag | - | Not available |
HumanEval | - | 88.4% pass@1 Source |
MATH | - | 77% 0-shot, CoT Source |
GPQA | 75.4% Diamond Source | 50.5% 0-shot, CoT Source |
IFEval | - | 92.1% Source |
Array | - | - |
AIME 2024 | - | - |
AIME 2025 | 75.5% Source | - |
Array | - | - |
Array | - | - |
Array | - | - |
Array | - | - |
Mobile Application | - |
Compare AI. Test. Benchmarks. Mobile Apps Chatbots, Sketch
Copyright © 2025 All Right Reserved.