Smallest Pulse Author Benchmark - mode not reported - English ESB - TED-LIUM - WER: leaderboard
Smallest Pulse Author Benchmark - mode not reported - English ESB - TED-LIUM - 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. 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. 8 models tracked. Updated 16 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Smallest AI Pulse | 2.52 | ||
| 2 | AWS Transcribe | smallest_pulse_author_benchmarks run | 2.66 | |
| 3 | Sarvam Saras V3 | smallest_pulse_author_benchmarks run | 2.89 | |
| 4 | Assembly Universal 3 Pro | smallest_pulse_author_benchmarks run | 2.95 | |
| 5 | ElevenLabs Scribe V2 | smallest_pulse_author_benchmarks run | 3.16 | |
| 6 | Deepgram Nova 3 | 3.59 | ||
| 7 | Azure | smallest_pulse_author_benchmarks run | 3.81 | |
| 8 | Grok | smallest_pulse_author_benchmarks run | 6.9 |
Interactive version: theaggregate.ai/benchmark?slug=smallest-pulse-author-benchmark-mode-not-reported-english-esb-ted-lium-wer · How It Works · Data refreshed daily, snapshot 2026-11-16.