← All benchmarks
FLEURS WER, streaming (top languages)
We haven't written a description for this benchmark yet; see the card notes below for how each maker ran it.
How each maker reported it
- Gemini 3.5 Transcribe Evaluation; launch post
The card links a separate methodology page and gives no numbers. WER figures are from Google's launch post, citing Artificial Analysis.
Only each model's own maker's number is shown; scores a maker reports for rival models are left out.