Meta

Llama 4 Maverick

A natively multimodal mixture-of-experts model with a practical active parameter count and a million-token context window for self-hosted or managed deployments.

open-weightsmultimodallong-context

Model record

Llama 4 Maverick model overview

Llama 4 Maverick is a open weights model from Meta. It was released on April 5, 2025. Its strongest case is downloadable weights, while buyers should account for community license is not osi-approved.

Llama 4 Maverick benchmark snapshot

EvaluationReported scoreWhat it probes
MMLU-Pro80.5Broad knowledge and multi-step reasoning
GPQA Diamond69.8Graduate-level science reasoning
SWE-bench VerifiedNot reportedVerified real-repository issue resolution
LiveCodeBench43.4Contamination-aware competitive programming
SWE-Bench ProNot reportedLonger, harder professional software tasks
Artificial Analysis Intelligence IndexNot reportedComposite third-party capability index; version matters

Scores are percentages reported by model creators or benchmark maintainers under varying settings. A blank is preferable to an inferred result. See our methodology.

Llama 4 Maverick strengths

  • Downloadable weights
  • Native image understanding
  • Efficient MoE activation

Llama 4 Maverick limitations

  • Community license is not OSI-approved
  • Serving full weights requires substantial hardware
Editorial take: Benchmark rank should narrow a shortlist, not close a purchase. Run a private evaluation with representative prompts, failure cases, latency targets, and total token costs.

Compare Llama 4 Maverick

Source record

Specifications and scores are linked to the best source located during review. Provider-reported results are not presented as third-party lab reproductions.

Read Meta model announcement