GPT-Live-1（Astra，medium）以 67.9% 领跑 Tau Voice，其次是 GPT-Live-1（Sol，low）的 59.3% 和 Grok Voice Think Fast 2.0 High 的 56.5%，推动其整体 Index 领先。两个 GPT-Live-1 配置目前均基于一次试验。在 Big Bench Audio 上，它们分别达到 90.1% 和 89.0%，落后于 Grok 的 97.2%。在我们的 Full Duplex Bench 子集上，它们分别得分 94.9% 和 97.3%；该基准与 Index 分开报告。
GPT-Live-1 (Astra, medium) leads Tau Voice at 67.9%, followed by GPT-Live-1 (Sol, low) at 59.3% and Grok Voice Think Fast 2.0 High at 56.5%, driving its overall Index lead. Both GPT-Live-1 configurations are currently based on one trial. On Big Bench Audio, they achieve 90.1% and 89.0%, respectively, behind Grok at 97.2%. On our Full Duplex Bench subset, they score 94.9% and 97.3%, respectively; this benchmark is reported separately from the Index.
来源：@ArtificialAnlys · x.com