While AVIF may have a slight edge in some cases like in fairly lossy compression, you won't really go _wrong_ with JPEG XL (unless strongly CPU constrained) and I think the strength of the format is its extreme versatility as a "be all end all image format" for some time where comparative performance depending on functionality ranges from respectable to excellent. It can work as a replacement for AVIF, PNG, JPEG, WebP, even certain TIFF required scenarios (high bit depth, multichannel, layers) depending on use cases.

Honestly, I think this will be a trend in 2027 when all those models become "good enough" for elite coding and whatever. I predict they'll have to branch out more and build their platform to differentiate themselves from each other, maybe even in terms of branding and trust, marketing towards various demographies, youth vs elderly, students vs employees, etc.

https://www.bridgebench.ai/nerf-bench

They test it on launch day, then benchmark it against that. A deviation of above 10% is considered a change. They're currently tracking Opus 5.5 and GPT-6 Astra.

This bench famously detected a degradation of Opus 4.6 which Anthropic later blogged about. I personally think people sense nerfs more often than they happen and that it's often about honeymoon effects.

I still remember the feeling of the ending, and the end credits music when the violin kicked in as it played the Manny & Meche theme! The music is at least as good as this game.

https://arcprize.org/results/anthropic-claude-opus-5

What OpenAI in particular have done with reasoning efficiency in the past few months since ChatGPT 5.5 is nothing short of remarkable. It's overshadowed a bit by the benchmark game and the Fable hoopla.

Now is the time to focus less on token cost and intelligence, but tokens to solve a particular set of tasks in closed benchmarks for a variety of categories.

What is the use of grand intelligence if it either costs you a kidney or can't complete at all within a token budget? Even if there are niche uses where you truly want "maximum power" above all, we need to at least more severely penalize such models versus those that does it just as fine within a tenth of the token cost.

I'm aware of some benchmarks at the Artificial Intelligence site, but CLEARLY we are not focusing enough on these today and still leaving the fun surprises to the users.

So then add a dash of cybersecurity and medical use and that's basically it. No "closer to AGI" advertising. I'd say the 2026 development has in fact been the opposite; optimizing AI for niches where there is most potential for profits and that your description died in circa GPT-5 era.

In fact, this problem (for this test) is also stated by the pelican test author:

"The biggest limitation of the pelican is that it doesn’t touch at all on the thing that matters most for today’s model: agentic tool calling and the ability to operate tools reliably as conversations grow in length.

So don’t go using pelicans to compare models!"