# GPT-6.1 Terra Ranks Eighth on Agent Arena With 10.6% Score By Simon Yoon Canonical URL: https://www.tokenpost.com/news/technology/43821 Published: 2026-10-29T19:48:01.000Z Updated: 2026-10-29T19:48:01.000Z Section: Technology > The model completed 50.3% of Terminal-Bench 4.0 tasks at maximum reasoning effort, compared with 21.5% for GPT-5.6 Terra. OpenAI’s GPT-6.1 Terra placed eighth on Agent Arena’s overall leaderboard, posting a 10.6% net-improvement score in a ranking of AI models’ work performed for users. Agent Arena evaluates models on work they carry out on a user’s behalf, rather than only on their answers to questions. The leaderboard lists Terra’s Max configuration in eighth place overall. OpenAI released GPT-6.1 Terra on Oct. 26 for visual reasoning, computer use and writing. On Terminal-Bench 4.0, Terra completed 50.3% of tasks at maximum reasoning effort, compared with 21.5% for GPT-5.6 Terra. TokenPost previously covered [GPT-6.1 Terra’s release and pricing](). ## Links in this article - [GPT-6.1 Terra’s release and pricing](https://www.tokenpost.com/news/technology/41451)