AssemblyAI Author Benchmark - streaming - Caller noise - Mean 3 conditions - WER: leaderboard

AssemblyAI Author Benchmark - streaming - Caller noise - Mean 3 conditions - WER — 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: WER (%). Source: https://www.assemblyai.com/benchmarks

Metric: WER (%). Source: www.assemblyai.com. Saturation forecast: Rough model projection: around 2026. 22 models tracked. Updated 16 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1AssemblyAI Universal-3.6 Pro5.19
2AssemblyAI Universal-3.5 Pro Realtimeassemblyai_author_benchmarks_2026 run5.72
3Soniox Realtimeassemblyai_author_benchmarks_2026 run6.83
4Meta Muse Voice Transcribeassemblyai_author_benchmarks_2026 run7.48
5ElevenLabs Scribe v2 Realtimeassemblyai_author_benchmarks_2026 run7.78
6Speechmatics Enhanced8.14
7Google Gemini 3.5 Transcribe Liveassemblyai_author_benchmarks_2026 run8.48
8AWS Transcribe Streamingassemblyai_author_benchmarks_2026 run8.58
9Deepgram Nova-3assemblyai_author_benchmarks_2026 run8.64
10Zoom Scribe (Live)assemblyai_author_benchmarks_2026 run9.36
11Reson8 Reson8assemblyai_author_benchmarks_2026 run9.41
12Mistral Voxtral Mini Realtimeassemblyai_author_benchmarks_2026 run10.43
13Smallest AI Pulse10.74
14Azure Realtime STTassemblyai_author_benchmarks_2026 run10.86
15Speechmatics Standard Realtimeassemblyai_author_benchmarks_2026 run12.05

Interactive version: theaggregate.ai/benchmark?slug=assemblyai-author-benchmark-streaming-caller-noise-mean-3-conditions-wer · How It Works · Data refreshed daily, snapshot 2026-11-16.