Leaked Future LLM Tier List: GPT-6 at the Top, Closed Frontier Far Exceeds Public Models

scaling01 · x · 2026-08-13

A user shared a predictive tier list for future large language models. In the expected ranking, GPT-6 Astra and Mythos 5.1 dominate the top, followed by Mythos 5, Opus 5, and GPT-5.5. Chinese models like Kimi-K3, Qwen 3.8, and DeepSeek-V4-Pro are also placed in the mid-to-high tiers. The core takeaway is that there is a massive gap between the current public state-of-the-art and the actual closed frontier hidden in labs.

Related event: Frontier LLM Competition Stagnates Amid Future Tier Predictions(6 posts)→

Original post →

More from AGI Musings

AGI Musings channel →