Technically not true any more (for some versions of copilot chat, at least) -- my workplace's version has a "GPT 5.6 Sol" selector with "Answer faster" or "Think Deeper". ("Think deeper" appears to represent the lowest reasoning effort).
But you have to select it each time; otherwise "Auto" sends you to a lobomised model that is probably Phi-4 :(
One of the unexpectedly useful aspects of Simon Willison's pelican benchmark is that you can estimate what model you're using via the pelican it generates:
"GPT 5.6 Sol": appears genuine, albeit low reasoning.
-> handed off agentically: appears to be using Luna for agentic tasks.
"Auto": very low quality, does not appear to be an OAI model.
alt Hacker News
Technically not true any more (for some versions of copilot chat, at least) -- my workplace's version has a "GPT 5.6 Sol" selector with "Answer faster" or "Think Deeper". ("Think deeper" appears to represent the lowest reasoning effort).
But you have to select it each time; otherwise "Auto" sends you to a lobomised model that is probably Phi-4 :(
One of the unexpectedly useful aspects of Simon Willison's pelican benchmark is that you can estimate what model you're using via the pelican it generates:
"GPT 5.6 Sol": appears genuine, albeit low reasoning. -> handed off agentically: appears to be using Luna for agentic tasks.
"Auto": very low quality, does not appear to be an OAI model.