AssemblyAI Author Benchmark - prerecorded - Diarization DER - Mean - DER: leaderboard

AssemblyAI Author Benchmark - prerecorded - Diarization DER - Mean - DER — 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: DER (%). Source: https://www.assemblyai.com/benchmarks

Metric: DER (%). Source: www.assemblyai.com. Saturation forecast: Rough model projection: around 2026. 9 models tracked. Updated 16 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1AssemblyAI Universal-3.5 Pro12.2
2Scribe v214.6
3Grok STTassemblyai_author_benchmarks_2026 run15.4
4Voxtral Mini Transcribe 2assemblyai_author_benchmarks_2026 run15.9
5Speechmatics Enhanced16.2
6Gladia Solaria-1assemblyai_author_benchmarks_2026 run16.7
7AWS Transcribeassemblyai_author_benchmarks_2026 run16.9
8Deepgram Nova 317.4
9Soniox v5 Async24.2

Interactive version: theaggregate.ai/benchmark?slug=assemblyai-author-benchmark-prerecorded-diarization-der-mean-der · How It Works · Data refreshed daily, snapshot 2026-11-16.