Skip to main content

Llama 4 Maverick

Meta

Meta's general-purpose open model. Easy to run and widely supported, though newer open models beat it on hard reasoning.

Released April 5, 2025

Pricing

Input tokensN/A/M
Output tokensN/A/M

Capacity

Context window1.0M tokens

Capabilities

Reasoning & Planning
Web Search
Open Source

Best Scores

GPQA Diamond69.8%
GDPval-AA v27.0 pts

Best For

✍️writing
📊analysis
📝summarization

Benchmark Scores

Knowledge

GPQA Diamond

PhD-level science questions written so you cannot just Google the answer. Tests whether the model can reason about hard science.

69.8%

Provider-reported; no independent run recorded yet.

Specialized Skills

GDPval-AA v2

Real paid work from 44 different jobs, such as law, nursing, and software. Judges compare two answers side by side without knowing which model wrote them, and the winner gains rating points. A typical human expert scores 1000, so a higher number means the work was picked over a human more often.

7.0 pts

Independently measured by Artificial Analysis.

Why Choose Llama 4 Maverick?

Llama 4 Maverick is the most widely supported open model in the ecosystem. Thousands of tools integrate with it, and it runs efficiently on consumer hardware. If compatibility and ease-of-use matter more than peak performance, Llama is the safe choice.

How It Compares

vs GLM-5.2

GLM is more capable on reasoning; Llama has broader tool support.

vs Qwen 3.6

Qwen is stronger on multilingual; Llama is more universally compatible.

You Might Also Like