Ming-3.0-audio-flash tops Artificial Analysis speech reasoning with 99.8% accuracy

victormustar · x · 2026-11-18

Ming-3.0-audio-flash claims the #1 spot on Artificial Analysis's Speech Reasoning leaderboard (Big Bench Audio) with 99.8% accuracy, edging out Grok Voice 3.0, Gemini 3.8 Live Extended Thinking (High), and GPT-Realtime-2.1 High. The leaderboard spans 42 models, with the lowest-scoring model at just 33.4%.

Related event: Ming-3.0 Audio Flash Tops Speech Reasoning Benchmark(2 posts)→

Original post →

More from Models

Models channel →