Skip to content
IFAI

Llama 4 Scout

Product2 stories

  1. AI modelsReach 47

    Meta denies artificially inflating Llama 4 benchmark scores

    Meta’s head of GenAI just denied rumors that Llama 4 Maverick and Scout were trained on test sets to game benchmark scores. The speculation flared over the weekend after users noticed performance gaps across platforms. Al-Dahle blamed the mixed quality on early rollout issues across cloud providers, promising bug fixes over the coming days.

  2. Open sourceReach 64

    Meta drops Llama 4 with MoE and 10M context

    Meta just unveiled Llama 4 Scout and Maverick, marking its official pivot to open-weight, natively multimodal mixture-of-experts architectures. Both models operate on 17B active parameters, with Scout pushing context windows to a massive 10 million tokens, while an upcoming 2T-parameter teacher model, Behemoth, trains in the background.