LLaMA 4 Maverick is a cutting-edge multimodal model featuring 17 billion active parameters within a Mixture-of-Experts architecture of 128 experts, totaling 400 billion parameters. It leads its class by outperforming models like GPT-4o and Gemini 2.0 Flash across a wide range of benchmarks, and it matches DeepSeek V3 in reasoning and coding tasks—using less than half the active parameters. Designed for efficiency and scalability, Maverick delivers a best-in-class performance-to-cost ratio, with an experimental chat variant achieving an ELO score of 1417 on LMArena. Despite its scale, it runs on a single NVIDIA H100 host, ensuring simple and practical deployment.
Llama 4 Maverick | GPT-4.1 Nano | |
---|---|---|
Provider | ||
Web Site | ||
Release Date | Apr 05, 2025 1 month ago | Apr 14, 2025 3 weeks ago |
Modalities | text images video | text images |
API Providers | Meta AI, Hugging Face, Fireworks, Together, DeepInfra | OpenAI API |
Knowledge Cut-off Date | 2024-08 | - |
Open Source | Yes (Source) | No |
Pricing Input | Not available | $0.10 per million tokens |
Pricing Output | Not available | $0.40 per million tokens |
MMLU | Not available | 80.1% Source |
MMLU Pro | 80.5% Source | - |
MMMU | 73.4% Source | 55.4% Source |
HellaSwag | Not available | - |
HumanEval | Not available | - |
MATH | Not available | - |
GPQA | 69.8% Diamond Source | 50.3% Diamond Source |
IFEval | Not available | 74.5% Source |
Array | - | - |
AIME 2024 | - | 29.4% Source |
AIME 2025 | - | - |
Array | - | - |
Array | - | - |
Array | - | 66.9% Source |
Array | - | 56.2% Image Reasoning Source |
Mobile Application | - |
Compare AI. Test. Benchmarks. Mobile Apps Chatbots, Sketch
Copyright © 2025 All Right Reserved.