AssemblyAI Author Benchmark - streaming - Common Voice multilingual - Chinese* - CER: leaderboard
AssemblyAI Author Benchmark - streaming - Common Voice multilingual - Chinese* - CER — 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. CER for Japanese/Chinese/Korean as marked by source. Metric: CER (%). Source: https://www.assemblyai.com/benchmarks
Metric: CER (%). Source: www.assemblyai.com. Saturation forecast: Rough model projection: around 2026. 17 models tracked. Updated 16 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | AWS Transcribe | assemblyai_author_benchmarks_2026 run | 8.5 | |
| 2 | AssemblyAI Universal-3.6 Pro | 9.2 | ||
| 3 | Azure | assemblyai_author_benchmarks_2026 run | 9.9 | |
| 4 | ElevenLabs Scribe v2 | assemblyai_author_benchmarks_2026 run | 12.1 | |
| 5 | AssemblyAI Universal-3.5 Pro | assemblyai_author_benchmarks_2026 run | 13.1 | |
| 6 | Google Gemini 3.5 Live | assemblyai_author_benchmarks_2026 run | 13.3 | |
| 7 | Soniox Realtime | assemblyai_author_benchmarks_2026 run | 14.1 | |
| 8 | Meta Muse Voice Transcribe | assemblyai_author_benchmarks_2026 run | 16.4 | |
| 9 | OpenAI GPT Realtime | assemblyai_author_benchmarks_2026 run | 16.4 | |
| 10 | Smallest AI Pulse | 18 | ||
| 11 | OpenAI GPT-4o mini Transcribe | assemblyai_author_benchmarks_2026 run | 19.3 | |
| 12 | OpenAI GPT-4o Transcribe | assemblyai_author_benchmarks_2026 run | 21.4 | |
| 13 | Speechmatics Enhanced | 25.1 | ||
| 14 | Speechmatics Standard | assemblyai_author_benchmarks_2026 run | 25.8 | |
| 15 | Gladia Solaria | assemblyai_author_benchmarks_2026 run | 29 |
Interactive version: theaggregate.ai/benchmark?slug=assemblyai-author-benchmark-streaming-common-voice-multilingual-chinese-star-cer · How It Works · Data refreshed daily, snapshot 2026-11-16.