Smallest Pulse Author Benchmark - mode not reported - WildASR public - Aggregate - WER: leaderboard
Smallest Pulse Author Benchmark - mode not reported - WildASR public - Aggregate - 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. mode not reported. Public WildASR degraded-condition dataset; no substitution with private perturbation panel. 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. 7 models tracked. Updated 16 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | ElevenLabs Scribe | smallest_pulse_author_benchmarks run | 6.47 | |
| 2 | Smallest AI Pulse | 7.6 | ||
| 3 | Azure | smallest_pulse_author_benchmarks run | 8.82 | |
| 4 | Assembly Universal 3 pro | smallest_pulse_author_benchmarks run | 12.52 | |
| 5 | Sarvam Saras V3 | smallest_pulse_author_benchmarks run | 17.75 | |
| 6 | AWS Transcribe | smallest_pulse_author_benchmarks run | 18.35 | |
| 7 | Deepgram Nova 3 | 28.17 |
Interactive version: theaggregate.ai/benchmark?slug=smallest-pulse-author-benchmark-mode-not-reported-wildasr-public-aggregate-wer · How It Works · Data refreshed daily, snapshot 2026-11-16.