WORLDTECHOpenAI puts GPT-6.1 Terra into Agent Arena and Code Arena for public testing
What happened
Last month when OpenAI released GPT-6 (large language model by OpenAI) models of Sol and Luna, its medium model Terra was excluded from the update. Now OpenAI has upgraded Terra from GPT-5.6 to GPT-6.1, touting speed and computer use at a lower price. OpenAI is an artificial intelligence company based in San Francisco.
26, 2026 OpenAI has added GPT-6.1 Terra to Agent Arena and Code Arena, giving users a chance to test the model on their own tasks. Public testing of GPT-6.1 Terra could redefine AI evaluation standards, offering insights into real-world applicability and cost efficiency.
They exist to let the community stress-test AI systems on practical agentic (AI that carries out multi-step tasks rather than answering one question) and coding work, rather than relying on the companies that built the models to grade themselves. From referee to contestant Terra’s earlier role makes this move interesting.
According to the research findings, Microsoft had referenced GPT-6.1 Terra as an internal model, with no public release date specified. In that setting, Terra served as a judge model for coding evaluations across 18 configurations.
The scale behind those measurements is substantial.
Agent Arena tracks over 2.5 million sessions and operates with causal tracing methodologies to evaluate AI performance. AI, tech, and the markets they move—in one daily briefing.