You are not missing anything. For 95% of dev work, sonnet, especially 3.5 and 3.7 has basically win opus, value per price.
in my experience the difference boils down to this
1. Sonnet is the faster. It's concise, follows instructions literally, and is significantly better at agentic tasks.
2. Opus is the philosopher. It’s better at high level architecture, creative writing, or spotting subtle nuances in a 50 pages document.
the reason your tests feel random is that for standard coding, sonnet is actually the superior model now. it is faster, less prone to over engineering, and has much lower latency.
if you have a massive, messy refactor where you need the model to reason through 10 files without adding bugs, opus might still have a slight edge in coherence. for everythng else, Sonnet is the meta. Stick with it and save the credits.