Smallest Pulse Author Benchmark - streaming - FLEURS - Portuguese - WER: leaderboard
Smallest Pulse Author Benchmark - streaming - FLEURS - Portuguese - WER — Smallest AI Pulse own author model-card evaluation, content hash pinned. Native model=pulse; never Pulse Pro or Pulse2. Comparator observations with unbound product versions retained as evaluation runs, not public model releases. Native percentage values unchanged; error rates unbounded above100. streaming. Metric: WER (%). Source: https://docs.smallest.ai/models/model-cards/speech-to-text/pulse
Metric: WER (%). Source: docs.smallest.ai. Saturation forecast: Rough model projection: around 2026. 3 models tracked. Updated 16 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Smallest AI Pulse | 8.32 | |
| 2 | Deepgram Nova 3 | 11.46 | |
| 3 | Deepgram Nova 2 | 14.15 |
Interactive version: theaggregate.ai/benchmark?slug=smallest-pulse-author-benchmark-streaming-fleurs-portuguese-wer · How It Works · Data refreshed daily, snapshot 2026-11-16.