aiaimodel.cards
← All benchmarks

Average WER, streaming (Artificial Analysis)

We haven't written a description for this benchmark yet; see the card notes below for how each maker ran it.

Your workloadRAG over docs · 12K in · 600 out · 50K requests/mo · 30% cached
  1. 1Gemini 3.5 Transcribe · Google
    4.0%

“Best value”: no other model here reports a higher score at a lower cost for your workload. Scores are self-reported by each maker with different settings, so treat close calls as ties.

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.