aiaimodel.cards
← All benchmarks

User preference, GA vs alpha

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. 1Eleven v3 · ElevenLabs
    72.0%

“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

  • Eleven v3 GA post

    ElevenLabs' own internal tests of the GA release against the alpha. Text-reading error rate covers an internal benchmark of 27 categories (phone numbers, scores, formulas, currencies, coordinates…) across 8 languages.

Only each model's own maker's number is shown; scores a maker reports for rival models are left out.