What I found interesting is that for the most part, the labs really aren't... except if you look at Otter Riding A Plane. That is close to Ethan Mollick's benchmark for diffusion image generation, Otter Using WiFi On A Plane. The results for DeepSeek and GLM look very much like Ethan's typical benchmark image output, which either means they're benchmaxxing... or they're the only two models that understand you ride inside a plane, not on top of it.
https://dylancastillo.co/posts/pelicanmaxxing.html
What I found interesting is that for the most part, the labs really aren't... except if you look at Otter Riding A Plane. That is close to Ethan Mollick's benchmark for diffusion image generation, Otter Using WiFi On A Plane. The results for DeepSeek and GLM look very much like Ethan's typical benchmark image output, which either means they're benchmaxxing... or they're the only two models that understand you ride inside a plane, not on top of it.