Llama 4 Scout
MMLU: 79.6, MMLU-Pro: 74.3, GPQA Diamond: 57.2, MMMU: 73.4, MathVista: 70.7, ChartQA: 88.8, DocVQA: 94.4, MGSM: 90.6 (multilingual), LiveCodeBench: 32.8 | Extreme long-context workloads (multi-document summarization, reasoning over vast codebases, long user-history personalization), native image+text understanding (charts, documents, captioning), multilingual chat across 12 languages, and single-GPU local/commercial deployment.
Empirical Evaluation Results
Architectural Profile & Capabilities
MMLU: 79.6, MMLU-Pro: 74.3, GPQA Diamond: 57.2, MMMU: 73.4, MathVista: 70.7, ChartQA: 88.8, DocVQA: 94.4, MGSM: 90.6 (multilingual), LiveCodeBench: 32.8 | Extreme long-context workloads (multi-document summarization, reasoning over vast codebases, long user-history personalization), native image+text understanding (charts, documents, captioning), multilingual chat across 12 languages, and single-GPU local/commercial deployment. The long-context + multimodal efficiency specialist of the Llama 4 line — not a frontier reasoning model
Standard dense autoregressive transformer architecture with full-attention mechanisms.
Recommended Workloads & Primary Use Cases
Calls to Llama 4 Scout are routed through strict Zero Data Retention inference channels. Prompts and outputs are never stored, indexed, or monitored by Meta Llama.
More Models from Meta Llama
Compare other engines available in this laboratory.