models · meta-llama
Meta's frontier Llama 4 Behemoth — 288B active MoE params, 10M token context, top-of-class multimodal reasoning.
| Weight file SHA-256 | f0a602414a4a2667c4d3acbf1e8c72577759d08a3b64d72d515cc359bc67995d |
|---|---|
| Method | closed-weights |
| Publisher | meta-llama |
|---|---|
| Origin | United States |
| Licence | Meta-Llama-4 |
| Pulls recorded here | 124,016 |
| GPQA Diamond | 88.5 |
|---|---|
| AIME 2025 | 89.1 |
Reported by a third party and recorded here, not re-run by us.
Registry record as of 2026-09-28. Identity, licence and parameter count are properties of a release and do not move; tier can, and the verify link above re-checks it against the live registry rather than this page.