AssemblyAI Author Benchmark - prerecorded - Accented English - British - WER: leaderboard

AssemblyAI Author Benchmark - prerecorded - Accented English - British - 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. 14 models tracked. Updated 16 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1AssemblyAI Universal-3.5 Pro5.3
2Scribe v25.5
3GPT-4o Transcribe5.7
4Voxtral Mini Transcribe 2assemblyai_author_benchmarks_2026 run5.8
5Gemini 3.5 Transcribe6.3
6AWS Transcribeassemblyai_author_benchmarks_2026 run6.5
7Speechmatics Enhanced6.7
8Grok STTassemblyai_author_benchmarks_2026 run6.8
9Azure Batch Transcriptionassemblyai_author_benchmarks_2026 run6.9
10Cohere Transcribe (language pinned)assemblyai_author_benchmarks_2026 run7.6
11parakeet-tdt-0.6B-v37.7
12Gladia Solaria-1assemblyai_author_benchmarks_2026 run7.8
13Soniox v5 Async8.2
14Deepgram Nova 39.3

Interactive version: theaggregate.ai/benchmark?slug=assemblyai-author-benchmark-prerecorded-accented-english-british-wer · How It Works · Data refreshed daily, snapshot 2026-11-16.