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

#ModelSettingScoreOverall rank
1Smallest AI Pulse2.52
2AWS Transcribesmallest_pulse_author_benchmarks run2.66
3Sarvam Saras V3smallest_pulse_author_benchmarks run2.89
4Assembly Universal 3 Prosmallest_pulse_author_benchmarks run2.95
5ElevenLabs Scribe V2smallest_pulse_author_benchmarks run3.16
6Deepgram Nova 33.59
7Azuresmallest_pulse_author_benchmarks run3.81
8Groksmallest_pulse_author_benchmarks run6.9

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.