> On what basis should one pick a model for a given task?

It's high-level (and doesn't break out coding/writing etc), but https://developers.openai.com/api/docs/models says:

> If you're not sure where to start, use GPT-6 Astra, our flagship model for complex reasoning and coding. Choose GPT-6.1 Sol to balance intelligence and cost, or GPT-6 Luna for cost-sensitive, high-volume workloads.

That page also seems to be updated after each new release.