Llama 4 Maverick 17B-128E is a model from Meta. This standardized model-evaluation pass uses the stored catalog profile as evidence: Open-weight, natively multimodal mixture-of-experts Llama 4 model with 17B active parameters, 128 experts, and a 1M-token context window.
The strongest available signals are catalog use-case guidance, 8 stated capabilities, 3 public technical links, pricing notes in the catalog row, 2 evidence families with sources. The current weighted score is 76.6/100, led by technical capability at 100/100, coding and agentic work at 90/100, and developer experience at 100/100.
The main caveats are some evidence searches failed and are recorded as warnings. Treat this pending evaluation as a Kainotomic expert draft that synthesizes available public evidence rather than a claim that we ran every benchmark ourselves.
