OpenAI 把 GPT-5.6 三兄弟 Sol、Terra 和 Luna 放到 Agent Arena 里了，能跑真实世界智能体任务，还能用网络和终端工具，去投个票就能影响排行榜。
OpenAI 推出的 GPT-5.6 系列包含 Sol、Terra 和 Luna 三个模型，已登陆 Agent Arena、ChatGPT、Codex 和 API。Agent Arena 在数百万真实世界长程智能体任务上评测模型，支持网页搜索、文件系统和终端工具。Leaderboard 采用因果追踪方法衡量模型输出相对于平均模型的效果。Sol 还额外支持搜索功能。用户投票将驱动排名更新。
GPT-5.6 Sol, Terra and Luna by @OpenAI are available in the Agent Arena! In Agent Arena, we measure...
GPT-5.6 Sol, Terra and Luna by @OpenAI are available in the Agent Arena! In Agent Arena, we measure models on millions of real-world, long-horizon agentic tasks from a global community of users. 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. In addition to Agent Arena, GPT-5.6 Sol, Terra and Luna are also available for: Text, Vision, Document and Code Arena: Frontend. Also available in Search for Sol. Head over and check it out, your votes drive the leaderboards. Scores incoming! OpenAI @OpenAI Sol, Terra, and Luna, our GPT‑5.6 family of models, are starting to roll out now in ChatGPT, Codex, and the API. Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 3 🔄 3 ❤️ 56 👀 5287 📊 7 ⚡