Other
AA-WER v2.0: Speech to Text Accuracy Benchmark
Artificial Analysis, 2026
Read the originalRead on October 17, 2026
- What it is
- An independent benchmark article from Artificial Analysis that defines its AA-WER v2.0 accuracy score, combines three datasets, and ranks batch speech to text models.
- How much weight it carries
- Independent, with a published method. The score is a weighted average of three datasets, so it can change if the weights or datasets change. Scores move between snapshots of the leaderboard.
Facts taken from this source
- 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.
“ElevenLabs Scribe v2 leads on two of the three component datasets, while Google's Gemini 3 Pro leads on VoxPopuli.” (Key results)
- In the Artificial Analysis AA-WER v2.0 benchmark, ElevenLabs Scribe v2 had the lowest error rate at 2.3 percent, ahead of Google's Gemini 3 Pro at 2.9 percent.
“ElevenLabs Scribe v2 leads at 2.3% AA-WER, followed by Google's Gemini 3 Pro at 2.9%” (Key results)
- In the Artificial Analysis AA-WER v2.0 key results, ElevenLabs Scribe v2 leads at 2.3 percent, followed by Gemini 3 Pro at 2.9, Voxtral Small at 3.0, Gemini 2.5 Pro at 3.1 and Gemini 3 Flash at 3.2 percent.
“ElevenLabs Scribe v2 leads at 2.3% AA-WER, followed by Google's Gemini 3 Pro at 2.9%, Mistral's Voxtral Small at 3.0%, Google's Gemini 2.5 Pro at 3.1%, and Gemini 3 Flash at 3.2%” (Key results)