AssemblyAI STT 3.7 Tops Voice Arena Streaming ASR Leaderboard at 2.45% WER
AssemblyAI · x · 2026-11-20
AssemblyAI's STT 3.7 Realtime Agent ranks #1 among all 17 streaming models on the Voice Arena US-English ASR leaderboard with 2.45% Semantic WER, and its Universal-3.6 Pro Realtime takes #2 at 2.50%. All models are evaluated on the same private set of 2,087 conversational US English clips.
More from Models
- GPT-6.2 Astra matches predecessor's MazeBench score at $225 vs $840 — patience_cave · 2026-11-20
- MazeBench: GPT-6.2 Sol narrows gap with Astra but still scores less at same price — patience_cave · 2026-11-20
- Gemini 4 Neon leads MazeBench on uncached token efficiency by a wide margin — patience_cave · 2026-11-20
- MazeBench: GPT-6.2 Astra tops at 16% while costing 25% of its predecessor — patience_cave · 2026-11-20
- Transparency Isn't Objectivity: Community Debates Bias in Model Reviews — RichardsonDx · 2026-11-19
- Fireworks launches Specialized Intelligence Index scoring models on domain benchmarks, cost and duration — sophiamyang · 2026-11-19