Artificial Analysis· @ArtificialAnlys · X·· 3 小时前AI 评分28
AI 导读
在我们的语音推理基准 Big Bench Audio 上，Grok Voice 3.0 得分 98.5%，领先 Gemini 3.8 Live Extended Thinking (High)（97.7%）和 Grok Voice 2.0（97.2%），落后于 StepAudio 3 Realtime 的 99.7%、Qwen Audio 3.0 Realtime Plus 的 99.2% 和 Qwen3.5 Omni Plus Realtime 的 98.7%。
正文
On Big Bench Audio, our speech reasoning benchmark, Grok Voice 3.0 scores 98.5%, ahead of Gemini 3.8 Live Extended Thinking (High) (97.7%) and Grok Voice 2.0 (97.2%), and behind StepAudio 3 Realtime at 99.7%, Qwen Audio 3.0 Realtime Plus at 99.2% and Qwen3.5 Omni Plus Realtime at 98.7%.
来源：Artificial Analysis · x.com