Comment by sashank_1509
10 hours ago
These ratings seems very wrong, i have beaten GPT Astra max thinking in chess and my rating is close to 1500. The ratings here seem more accurate: https://chessbenchllm.onrender.com/
GPT-6 almost never suggests an illegal move anymore while even Sol still did so time to time
"Elo is relative to the ChessBench field."
They are of course "wrong" if you don't read the faint fine print and sensibly interpret them as FIDE or similar ratings.