Heavy AI spender ranks models, leaves Gemini Argon untested
A user spending thousands monthly on AI ranks models from best to worst, calling Opus 5.5 all-round and GPT Astra poor at UI, while noting he hasn't tried Muse Wonder or Gemini Argon.
I'm spending thousands monthly on AI models and AI subs so this is how I would rate current models from order of best to worse (I haven't tried Muse Wonder nor Gemini Argon so I can't speak for those) - Opus 5.5: Goated, can do everything, great taste and aesthetic sense, ultimate UI builder - GPT Astra: Good for most stuff and hard non coding problems, absolutely ass at any UI development, horrible taste - Grok 4.7: Super fast, insane workhorse, beats K3 and GLM in all my benchmarks of onchain investigations both in speed and accuracy - Abliterated Large v2: IYKYK - Kim K3 and GLM 5.3 : Good workhorses and good to delegate non critical development and data analysis, a bit slow - GPT 6.1 SOL: LOL 🤣🤣 wtf is this trash, dont trust it for anything code related, good for data analysis or non development work