mark_k: GPT-6.2 Sol is 'so freaking efficient', barely uses tokens
mark_k · x · 2026-11-22
markk praises GPT-6.2 Sol for being remarkably token-efficient, saying it "just goes on and on without using many tokens" and that lesser models like Terra are no longer needed.
More from Models
- Neon balances speed and intelligence well, though Opus 5.5 still wins at videos — omarsar0 · 2026-11-22
- Yacine: Claude 5.5 'just not very good', pales compared to Neon — yacineMTB · 2026-11-22
- Wenhu Chen Revives 'But Can They Reason?' Debate, Asking Why Critics Went Silent — WenhuChen · 2026-11-22
- Gemini 4 Neon hits 59% on rare-disease benchmark, near Claude Fable 5.2 at lower cost — danielmckinn0n · 2026-11-22
- Tesla AI lead: new system uses less compute than the old one did — aelluswamy · 2026-11-22
- JUP-Eval tests whether models hold correct answers under user pushback, not just once — geoffwolfe · 2026-11-22