GPT-6.1 arrives in Agent Arena and Code Arena

Arena says it compared 34,580 model verdicts with human votes across 1,460 battles. On average, a judge chose its own answer 58% of the time, while people chose that same answer 34% of the time.

Agent Arena's later update puts the model at +1.59% net improvement and a $0.05 median cost per task, reversing an earlier post that said it had missed the frontier.