AssemblyAI Author Benchmark - streaming - Code switching - EN↔PT - WER: leaderboard
AssemblyAI Author Benchmark - streaming - Code switching - EN↔PT - 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. 23 models tracked. Updated 16 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | AssemblyAI Universal-3.6 Pro | 7 | ||
| 2 | AssemblyAI Universal-3.5 Pro Realtime | assemblyai_author_benchmarks_2026 run | 8.71 | |
| 3 | Reson8 Reson8 | assemblyai_author_benchmarks_2026 run | 9.67 | |
| 4 | Google Gemini 3.5 Transcribe Live | assemblyai_author_benchmarks_2026 run | 9.79 | |
| 5 | AWS Transcribe Streaming | assemblyai_author_benchmarks_2026 run | 9.81 | |
| 6 | Soniox Realtime | assemblyai_author_benchmarks_2026 run | 11.18 | |
| 7 | ElevenLabs Scribe v2 Realtime | assemblyai_author_benchmarks_2026 run | 13.79 | |
| 8 | Meta Muse Voice Transcribe | assemblyai_author_benchmarks_2026 run | 14.85 | |
| 9 | Azure Realtime STT | assemblyai_author_benchmarks_2026 run | 15.03 | |
| 10 | Gladia Solaria | assemblyai_author_benchmarks_2026 run | 15.93 | |
| 11 | Smallest AI Pulse | 16.73 | ||
| 12 | Deepgram Nova-3 Multi | assemblyai_author_benchmarks_2026 run | 17.29 | |
| 13 | Mistral Voxtral Mini Realtime | assemblyai_author_benchmarks_2026 run | 17.43 | |
| 14 | xAI Grok Streaming | assemblyai_author_benchmarks_2026 run | 20.79 | |
| 15 | OpenAI GPT-4o mini Transcribe | assemblyai_author_benchmarks_2026 run | 32.07 |
Interactive version: theaggregate.ai/benchmark?slug=assemblyai-author-benchmark-streaming-code-switching-en-pt-wer · How It Works · Data refreshed daily, snapshot 2026-11-16.