AssemblyAI Author Benchmark - streaming - Healthcare entities - Dictation - Medical entity error rate: leaderboard
AssemblyAI Author Benchmark - streaming - Healthcare entities - Dictation - Medical entity error rate — 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: Medical entity error rate (%). Source: https://www.assemblyai.com/benchmarks
Metric: Medical entity error rate (%). Source: www.assemblyai.com. Saturation forecast: Rough model projection: around 2026. 22 models tracked. Updated 16 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Meta Muse Voice Transcribe | assemblyai_author_benchmarks_2026 run | 3.09 | |
| 2 | Speechmatics Enhanced | 3.65 | ||
| 3 | Soniox Realtime | assemblyai_author_benchmarks_2026 run | 4.04 | |
| 4 | AssemblyAI Universal-3.6 Pro | 4.2 | ||
| 5 | AssemblyAI Universal-3.5 Pro Realtime | assemblyai_author_benchmarks_2026 run | 5.08 | |
| 6 | OpenAI GPT Realtime | assemblyai_author_benchmarks_2026 run | 5.39 | |
| 7 | Google Gemini 3.5 Transcribe Live | assemblyai_author_benchmarks_2026 run | 7.69 | |
| 8 | ElevenLabs Scribe v2 Realtime | assemblyai_author_benchmarks_2026 run | 8.01 | |
| 9 | Zoom Scribe (Live) | assemblyai_author_benchmarks_2026 run | 8.09 | |
| 10 | OpenAI GPT-4o Transcribe | assemblyai_author_benchmarks_2026 run | 14.91 | |
| 11 | Mistral Voxtral Mini Realtime | assemblyai_author_benchmarks_2026 run | 16.02 | |
| 12 | AWS Transcribe Streaming | assemblyai_author_benchmarks_2026 run | 16.49 | |
| 13 | Deepgram Nova-3 | assemblyai_author_benchmarks_2026 run | 17.37 | |
| 14 | Deepgram Flux EN | assemblyai_author_benchmarks_2026 run | 18.32 | |
| 15 | Speechmatics Standard Realtime | assemblyai_author_benchmarks_2026 run | 18.72 |
Interactive version: theaggregate.ai/benchmark?slug=assemblyai-author-benchmark-streaming-healthcare-entities-dictation-medical-entity-error-rate · How It Works · Data refreshed daily, snapshot 2026-11-16.