Grok Voice 3.0 scores 98.5% on Big Bench Audio, behind three rival voice models

Artificial Analysis reports that Grok Voice 3.0 scores 98.5% on Big Bench Audio, its speech reasoning benchmark.

That places it above Gemini 3.8 Live Extended Thinking (High) at 97.7% and Grok Voice 2.0 at 97.2%. It trails StepAudio 3 Realtime at 99.7%, Qwen Audio 3.0 Realtime Plus at 99.2% and Qwen3.5 Omni Plus Realtime at 98.7%.

The scores come from Artificial Analysis's own benchmark. The report does not describe the test setup beyond naming the benchmark.