LLM compare · detail

Llama 4 Maverick

Provider: Meta

Model type: specialist Budget: open / self-run Use it for: self-hosted stack Use it for: sensitive deployments Use it for: company knowledge

self-hosted pick backed by current AA.

Verdict „Llama 4 Maverick has IQ 18.4 and input $0.35/M in the sources. Consider it for self-hosted stack, sensitive deployments; for managed-api-comfort, deep-frontier-reasoning, run a second benchmark before rollout."

Snapshot summary

Meta maintains Llama as an open-weight base for developers, hosters and companies that want to run or adapt models outside closed APIs. Llama 4 Maverick is Meta's open-weight model for own hosting, tuning and the tooling ecosystem around the Llama family.

In this compare snapshot it is tagged mainly for self-hosted, compliance, rag, with price tier free-open and context window není v ověřených datech. The negative side matters too: watch managed-api-comfort, deep-frontier-reasoning. Use the numbers below as the hard boundary, because this profile explains the model, it does not replace benchmark provenance.

Figures below, fetched from source artificial_analysis (fetched 2026-06-14T04:00:40Z).

Snapshot figures

self-hosted Budget provider-dependent

18.4 intelligence index artificial_analysis:llama-4-maverick

What this means

✓ Good for: self-hosted · compliance · rag

✗ Not for: managed-api-comfort · deep-frontier-reasoning

Source and provenance

Data source: artificial_analysis
Fetched: 2026-06-14T04:00:40Z
Status per metric: price: artificial_analysis:llama-4-maverick; IQ: artificial_analysis:llama-4-maverick; Elo: curated_seed; Aider: curated_seed; DeepSWE: curated_seed

This page shows only verified data from the current snapshot.