AssemblyAI Author Benchmark - prerecorded - Diarization cpWER - DiPCo - cpWER: leaderboard
AssemblyAI Author Benchmark - prerecorded - Diarization cpWER - DiPCo - cpWER — AssemblyAI primary author evaluation, captured 2026-11-16; no fusion with another campaign sharing a corpus. Exact system versions and run ranges retained in source_systems_rosters. Prerecorded: public API defaults, auto language except explicitly pinned Cohere/Azure; models shown only when >=90% of files returned relative to AssemblyAI. Streaming: real-time SDK/WebSocket delivery, fixed language, final transcripts rather than partials, shared normalization. All streaming 0.00 means no data. Language WER/CER >=60 means unsupported. Language-specific boards join all-language and partial-language rosters but exclude incomparable means over different supported languages. Native percentage error; no upper cap of100. Metric: cpWER (%). Source: https://www.assemblyai.com/benchmarks
Metric: cpWER (%). Source: www.assemblyai.com. Saturation forecast: Rough model projection: around 2026. 9 models tracked. Updated 16 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | AssemblyAI Universal-3.5 Pro | 29.1 | ||
| 2 | Scribe v2 | 34.3 | ||
| 3 | Speechmatics Enhanced | 35.5 | ||
| 4 | AWS Transcribe | assemblyai_author_benchmarks_2026 run | 35.5 | |
| 5 | Deepgram Nova 3 | 37.2 | ||
| 6 | Voxtral Mini Transcribe 2 | assemblyai_author_benchmarks_2026 run | 39.3 | |
| 7 | Soniox v5 Async | 42.4 | ||
| 8 | Grok STT | assemblyai_author_benchmarks_2026 run | 43.4 | |
| 9 | Gladia Solaria-1 | assemblyai_author_benchmarks_2026 run | 43.5 |
Interactive version: theaggregate.ai/benchmark?slug=assemblyai-author-benchmark-prerecorded-diarization-cpwer-dipco-cpwer · How It Works · Data refreshed daily, snapshot 2026-11-16.