Llama 3.1 405B
MetaLLMs
88.4
Performance
★ 4.4
Rating
420
Reviews
ReasoningLargeText GenerationOpen Weight
About
Meta's largest open-weight model with 405 billion parameters, designed for enterprise-grade reasoning, coding, and multilingual tasks.
Strengths
One of the strongest open-weight models. Excellent for self-hosting, fine-tuning, and data-sovereign deployments. Strong on general reasoning, coding, and knowledge tasks. Llama license allows broad commercial use.
Specifications
- Context window
- 128,000
- Parameters
- 405B
Pricing
- Input cost
- Free
- Output cost
- Free
Open-weight model. Free to download. Hosting costs vary: ~$1-4/1M tokens on major providers.
Speed & Latency
- 150
- tokens/sec
- 285ms
- time to first token
Available On
HuggingFaceTogether AIFireworks AIGroqAmazon BedrockAzure AI
Features
function callingstreamingsystem messages
Performance Trend
Benchmark score trends over time for the top 5 benchmarks.
Loading history...
Benchmarks
Scores from various benchmark tests; higher is better.
| Test | Score | Percentile | Source |
|---|---|---|---|
| ARC-Challenge | 87.6 | — | huggingface |
| BigBench Hard | 82.3 | p93 | seed |
| Chatbot Arena ELO | 1126.0 | — | chatbot-arena |
