I've been testing Claude Fable / Mythos 5.1 + Opus 5.0 + GPT Image 2.0 + Seedance 2.5 to cook ALL our winning Meta ads inside 1 conversation...
And it has been ABSOLUTELY cooking so i've decided to document the ENTIRE workflow of producing 100 winning Meta ad creatives in
Gemini 3.8 Flash vs Opus 5
Same prompt to each model and i wasn't expecting gemini 3.8 flash to be this fast! build time: Opus 5: 24 minutes 3.8 Flash: 37 seconds 💀 if gemini is given same time as opus 5 it will mog the hell out of opus in terms of quality too which one
This is why my benchmark is not benchmaxxable and is one of the best on social
Put Gemini 3.8 High against Opus 5 xHigh and the hype does not hold up. It got mogged hard. No real leap here, just obvious benchmark-maxxing I have heavy constraints in this test, so it clearly
Gemini 3.8 Flash Boeing 737 ThreeJS build.
Camera is broken, the build has weird transparency issues. The model seems very benchmaxed, Opus 5, Fable 5./5.1, GPT-5.6 and chinese models, even GLM 5.3 Flash seem to provide better results for me. Maybe Gemini 4 will be better..
You have reached the end of the archive
All of Claude Opus 5