Fact · Speech recognition
In the same Artificial Analysis benchmark, ElevenLabs Scribe v2 leads on two of three datasets, and Google's Gemini 3 Pro leads on the parliamentary VoxPopuli dataset.
Checked against its source on October 17, 2026
In the source's own words
“ElevenLabs Scribe v2 leads on two of the three component datasets, while Google's Gemini 3 Pro leads on VoxPopuli.”
AA-WER v2.0: Speech to Text Accuracy Benchmark, Artificial Analysis, 2026, Key results.
Open the original- What it measures
- The result shows that the overall ranking depends on which kind of speech you have. Parliamentary speech is different from voice-agent speech or earnings calls.
- What it does not show
- The article gives the component scores, and the ranking can move between leaderboard snapshots.