Boson AI's 45B MoE duplex model tops Big Bench Audio at 98.9, beating TML and Google Live
smolix · x · 2026-11-06
Boson AI unveiled Higgs Realtime Duplex, a 45B MoE model for full-duplex audio and video conversations, with self-reported benchmarks:
- Big Bench Audio: 98.9, highest in its comparison, ahead of Thinking Machines' 276B model with background agent (96.5)
- Beats Google's Live models on 6 of 7 benchmarks and TML on 4 of 6
- Second place on Audio MultiChallenge, Full-Duplex-Bench v1.5, QIVD, ProactiveVideoQA, t-Voice and IFEval; some metrics trail top-tier GPT Realtime configs
- Self-reported scores, pending independent verification
Related event: Boson AI Unveils 45B MoE Full-Duplex Audio-Video Model(3 posts)→
More from Models
- Artificial Analysis launches Intelligence Index v5 and new Progress Index, reveals eval roadmap — ArtificialAnlys · 2026-11-06
- 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