Llama 4
Meta
partial detail 10 method fields published
Evaluation
Standard benchmark evaluations (pre-trained and instruction-tuned models)
Standard automatic benchmark results reported for Llama 4 pre-trained and instruction-tuned models (all reported evaluations and testing conducted on bf16 models)
How it was run
Open a release to see the setup, scoring, and other details that the lab published. Only fields the lab actually disclosed are shown.