AssemblyAI Author Benchmark - streaming - Diarization - DER - DiPCo - DER: leaderboard

AssemblyAI Author Benchmark - streaming - Diarization - DER - DiPCo - 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. 12 models tracked. Updated 16 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1Meta Muse Voice Transcribeassemblyai_author_benchmarks_2026 run14.81
2Reson8 Reson8assemblyai_author_benchmarks_2026 run15.98
3AssemblyAI Universal-3.5 Pro Realtimeassemblyai_author_benchmarks_2026 run21.29
4AssemblyAI Universal-3.6 Pro22.1
5Azure Realtime STTassemblyai_author_benchmarks_2026 run24.3
6Speechmatics Standard Realtimeassemblyai_author_benchmarks_2026 run24.68
7Soniox Realtimeassemblyai_author_benchmarks_2026 run27.23
8Speechmatics Enhanced28.37
9AWS Transcribe Streamingassemblyai_author_benchmarks_2026 run32.09
10xAI Grok Streamingassemblyai_author_benchmarks_2026 run35.28
11Deepgram Nova-3assemblyai_author_benchmarks_2026 run45.35
12Smallest AI Pulse50.98

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