Comprehensive benchmark scores, coding performance, latency metrics, and API pricing for all models developed by Meta.
Portfolio at a glanceRanked catalog of 5 Meta models.
Meta's first open-weights release since Llama 4: a dense 30B multimodal model under Apache 2.0, distilled from Muse Spark for agents on local hardware.
Model fact sheetMuse Image is an agentic image generation model from Meta that generates and edits images from text and reference images. Unlike single-pass image models, it reasons before it renders, breaking...
Model fact sheetMuse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context...
Model fact sheetMuse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, audio, and PDF documents, returns text, and offers a 1M-token context...
Model fact sheetMeta's multimodal reasoning model for long-running agentic, multi-agent and coding workflows.
Model fact sheetJump straight to their strongest model, or compare the lab against its peers.
Compare any two models on our category ratings, speed classes and token pricing.
Targeted rankings for Best Coding LLMs, Best Cheap APIs, Shortest Wait, and top-tier models.
Interactive VRAM calculator, quantization levels (FP16, Q8, Q4), KV cache context, and local hardware fit.
Live audit trail of benchmark updates, new model releases, and API price cuts.
Answer 5 quick questions to compute deterministic model recommendations for your use case.
How a CompareLLM rating is computed, what evidence it admits, and how prices and speed classes are recorded.
