Llama 4

Meta AI · Open-weight · 4

Meta's flagship open-weight model. Competes with frontier closed models on many benchmarks.

Status
active
Release date
2026-04-01
Parameters
405B
Context window
128K
Modalities
text,code,image
Capabilities recorded
tool use, API, local use
Last verified
2026-07-20

Reviewed use cases

  • local deployment
  • research
  • fine-tuning

Recorded limitations

  • Requires significant hardware for full precision

Benchmark Performance

This model has results from 1 benchmark, but fewer than 2 distinct benchmarks — insufficient for a TRACE aggregate score.

BenchmarkScoreProvenanceDateSource
MMLU-Pro 84.0% Vendor 01/07/2026 Source

Pricing is omitted until provider-model pricing rows have their own completed review and publication state.