/ Models Index / Llama 4 Maverick

Llama 4 Maverick

Open-Weights · Meta · Meta AI · Released Apr 2025
B+

Good (B+) — Capability Grade

Llama 4 Maverick is Meta's mid-tier open-weights model. Strong cost-efficiency for on-premise deployment. Mid-tier reasoning vs. Behemoth; competitive with closed-source small models.

83
Composite / 100
/ Subscore Breakdown · 6 Capability Dimensions

Where this grade comes from.

General Reasoning
B
Code Generation
B
Math & STEM
B
Tool Use & Agency
B-
Multimodal
B+
Safety & Alignment
B
/ Key Events & Disclosures

Release timeline & positioning.

  • Released Apr 2025
  • Mid-tier open-weights
  • MoE architecture
  • Strong on-premise deployment economics

/ Best for

Cost-sensitive on-premise deployments and fine-tuning workflows.

/ Watch out for

Frontier benchmarks lag closed-source frontier models. Best as open-weights baseline, not state-of-art replacement.