Llama 5
Meta AI · · 368 days after Llama 4 Maverick
Partially verified
0 of 1 published values traced to a source0 primary sources, 1 archived3 not researched yet
Why this status
No primary source. The release is recorded from news reporting only, so it cannot be verified until the lab's own announcement is cited.
What these states mean · How records are judged · Has this record changed?
Meta's first MoE flagship, marking a major architecture shift for the open family.
Details
| Released | April 8, 2026 |
|---|---|
| Company | Meta AI |
| Family | Llama |
| Lineage | after Llama 3.2 |
| Era | Agentic systems |
| Type | Language model · LLM |
| Modalities | Not recorded |
| Capabilities | Not recorded |
| Weights | Open weights |
| Licence | Not researched |
| Context window | Not researched |
| Parameters | Not researched |
Current information, elsewhere
This record is a historical one: every figure above is traced to a dated primary source. For what is true today — live pricing, current rankings, availability — these are better maintained than anything here could be.
- Current price and providers OpenRouter ↗
- Current benchmark scores Artificial Analysis ↗
- Weights and model card Hugging Face ↗
Sources
Record status: partly verified · confidence 60/100 · 0 of 1 primary
No primary source. The release is recorded from news reporting only, so it cannot be verified until the lab's own announcement is cited.
- en.wikipedia.org News reporting archived
Primary means published by the organisation that made the model. Verified records require at least one.
Llama family
- Llama 1 February 24, 2023
- Llama 2 July 18, 2023
- Llama 3 April 18, 2024
- Llama 3.1 July 23, 2024
- Llama 3.2 September 25, 2024
- Llama 4 Scout April 5, 2025
- Llama 4 Maverick April 5, 2025
- Llama 5 April 8, 2026
What changed from Llama 3.2
Compared with the previous release in this series. A field appears only when both records state a value — where one does not, it is listed as uncomparable rather than dropped, because a gap in our research is not a finding about the model.
Not comparable: Context window (not researched on both releases); Parameters (not researched on both releases); Licence (not researched on both releases); Capabilities and modalities (not researched on both releases)
Compare Llama 5 with another model →
See Llama 5 on the interactive timeline →