AssemblyAI Universal 3.6 Pro tops clean-audio STT benchmark with 1.77% WER
AssemblyAI · x · 2026-11-06
Per the Cekura Bench STT leaderboard, AssemblyAI Universal 3.6 Pro achieves the lowest word error rate on clean audio at 1.77%, beating NVIDIA Nemotron 3.5 Transcribe (1.89%), Fish Audio Transcribe Stream 1 (1.90%), its predecessor Universal 3.5 Pro (1.93%), and Google Chirp 3 (2.00%) among 19 models. Final transcripts land 91ms after the caller stops speaking, highlighting strong real-time latency.
More from Models
- GPT-6 Cyber 'lightyears ahead of everything', says researcher after OpenAI early-adopter reveal — Eric_Wallace_ · 2026-11-06
- Fastino open-sources GLiDE: five decision models (0.4B-27B) claiming a new Pareto frontier — HowDevelop · 2026-11-06
- V0.5 model released with technical report, Hugging Face weights and inference code — rohanpaul_ai · 2026-11-06
- Clairvoyance launches Local AI benchmark site: 31 models × 15 hardware configs — draginol · 2026-11-06
- webAI Claims 12B Model Beats Gemini and Claude, But the Benchmark Claims Raise Eyebrows — eurie_kim · 2026-11-06
- User cancels OpenAI over Codex quota change, says Claude did a week's work in 4.5 hours — LethalLuck7 · 2026-11-06