AssemblyAI Author Benchmark - prerecorded - Code switching - Long EN-ES - WER: leaderboard

AssemblyAI Author Benchmark - prerecorded - Code switching - Long EN-ES - 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. 13 models tracked. Updated 16 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1Scribe v25.8
2AssemblyAI Universal-3.5 Pro6.1
3Soniox v5 Async8.4
4Voxtral Mini Transcribe 2assemblyai_author_benchmarks_2026 run10.5
5Azure Batch Transcriptionassemblyai_author_benchmarks_2026 run16.1
6AWS Transcribeassemblyai_author_benchmarks_2026 run16.7
7Grok STTassemblyai_author_benchmarks_2026 run28.4
8GPT-4o Transcribe33
9Cohere Transcribe (language pinned)assemblyai_author_benchmarks_2026 run33
10Gemini 3.5 Transcribe40.8
11Deepgram Nova 343.2
12Gladia Solaria-1assemblyai_author_benchmarks_2026 run43.3
13parakeet-tdt-0.6B-v354.1

Interactive version: theaggregate.ai/benchmark?slug=assemblyai-author-benchmark-prerecorded-code-switching-long-en-es-wer · How It Works · Data refreshed daily, snapshot 2026-11-16.