GPT-6 Sol and Luna arrive in Agent Arena and Code Arena for voting
Agent Arena and Code Arena have added GPT-6 Sol and Luna, and user votes will shape their leaderboard evaluations.
GPT-6 Sol and GPT-6 Luna by @OpenAI are now in the Arena! Head to Agent Arena to test them out, and your votes will shape their evaluations. Scores coming soon. In Agent Arena, we measure models on millions of real-world, long-horizon agentic tasks. Models can access web search, filesystem, and terminal tools to complete complex workflows. The leaderboard measures model performance on outcomes relative to the average model using a causal tracing methodology. GPT-6 Sol and Luna are also available in Code Arena: WebDev, Text, Vision, Search and Document.
This post quotes another post: “OpenAI releases GPT-6 Sol and Luna with 50% lower API prices”