forgot-my-pw

This is insanity. So much destruction and loss :(

This is good. Probably to match GPT pricing, though frontier Claude models are still not as token efficient.

Not sure on the API side, in Cursor you can always use 4.6 at xhigh.

Late reply: I'm not sure which chart you're referring to. The top 2 charts shows Astra has the same score as Fable 5.1. Even the title says "GPT-6 Astra ties leadership with Claude Fable 5.1 in both of our flagship Indices, at lower cost. Astra equals Fable 5.1 in the Intelligence Index at ~40% of the cost, and in the Coding Agent Index at ~60% of the cost."

Terminal Bench 2/2.1 appears to be almost solved, so we probably shouldn't look too hard on that? Their Terminal Bench 4 score is soso.

Still quite impressive though.

We need them pelicans on bikes.

Time for Gemini 3.8 Flash to shine?!

It's much cheaper and has replaced Sonnet 5 for me.

The art of premature optimizations

Why not both!

We need to eliminate human drivers in the future. So the best solution should be both self driving cars and public transportation.

I have done some variation of the other animals, also for something more tricky where they need to calculate things, I ask them to draw an SVG at a certain angle.

For example: "generate an SVG of a chessboard seen from a 45 degree angle slightly higher POV" or "generate an SVG of a basketball court from a TV broadcast perspective".

I find Gemini is still the best at creating SVGs.

Even with the new benchmark, Composer 2.5 seems to be just a bit worse than Opus 4.7. So I assume it's going to be about similar with Sonnet 5.0 at 1/6 of the cost.

I find when working with just a single model (Codex / Claude Code), it tends to have more blind spots. So it's nicer to have different models review each others.

Also with Cursor you can make plans with more expensive models and execute using cheaper ones like Composer 2.5.