Every model,
opened up.

Architecture, training, strengths and weaknesses for each frontier model — Fable 5, Mythos 5, Opus 4.8, GPT-5.5, Gemini 3.1 Pro & 3.5 Flash, Grok 4.3, DeepSeek V4-Pro and the rest. Auto-updated daily; also mirrored as markdown in /research/model-deep-dives.