Smallest Pulse Author Benchmark - mode not reported - WildASR public - Phone Codec - WER: leaderboard

Smallest Pulse Author Benchmark - mode not reported - WildASR public - Phone Codec - 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. 6 models tracked. Updated 16 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1Assembly Universal 3 prosmallest_pulse_author_benchmarks run3.45
2ElevenLabs Scribesmallest_pulse_author_benchmarks run4.98
3Smallest AI Pulse6.64
4AWS Transcribesmallest_pulse_author_benchmarks run8.7
5Deepgram Nova 39.13
6Sarvam Saras V3smallest_pulse_author_benchmarks run10.64

Interactive version: theaggregate.ai/benchmark?slug=smallest-pulse-author-benchmark-mode-not-reported-wildasr-public-phone-codec-wer · How It Works · Data refreshed daily, snapshot 2026-11-16.