TAAFT
Free mode
100% free
Freemium
Free Trial
Deals

Llama 4 Behemoth

Model family: LLaMA
Large Multimodal Model (Teacher); MoE architecture (16 experts, 288B active, ~2T total params); Used to distill Llama 4 Scout/Maverick; Outperforms GPT-4.5/Claude 3.7 Sonnet/Gemini 2.0 Pro on STEM benchmarks; Still in training (as of Apr 2025).
Multimodal Gen 3
Released: April 5, 2025

About Meta Platforms

We're connecting people to what they care about, powering new, meaningful experiences, and advancing the state-of-the-art through open research and accessible tooling.

Industry: Technology, Information and Media
Company Size: 78865
Location: Menlo Park, California, US
Website: ai.meta.com
View Company Profile

Benchmark scores

How Llama 4 Behemoth ranks on tracked AI benchmarks. Click any benchmark to see its full leaderboard.

49.4%
95.0%
GPQA Diamond
Knowledge
73.7%
MMLU-Pro
Knowledge
82.2%
MMMU
Multimodal
76.1%
Compare across all benchmarks โ†’

Tools using Llama 4 Behemoth

Last updated: April 6, 2026
0 AIs selected
Clear selection
#
Name
Task