Sesame releases TurnBench, an open benchmark for voice AI turn-taking
realmrfakename · x · 2026-08-29
Sesame released TurnBench, an open-source benchmark for evaluating turn-taking in spoken dialogue: whether voice AI knows when a user's turn is truly over, and whether an "mm-hmm" is agreement rather than an interruption.
- The typical gap between human turns is only 200 ms, shorter than the 600 ms needed to plan a single word — listeners predict turn ends from prosodic and linguistic cues rather than reacting to silence.
- Interruptions, talking over users, and awkward silences remain common failures that instantly break the illusion of a natural voice assistant.
- TurnBench mirrors Sesame's internal evaluation methodology (same taxonomy, tasks, scoring), with a public leaderboard, interactive conversation viewer, and self-serve dev-set scoring, built with partners including Carnegie Mellon University and Mundo AI.
More from Models
- Unsloth releases GLM-5.3 GGUF version for local deployment — burny_tech · 2026-08-29
- GLM-5.3-Flash writes Blender script for automotive museum live — mishig25 · 2026-08-29
- Polymarket predicts 69% chance of Grok 5 release by year-end — Polymarket · 2026-08-29
- Community reacts to GLM-5.3 full weight release with 'My weights, my choice' — examachine · 2026-08-29
- GLM 5.3 Available in Perplexity Computer, Beats GLM 5.2 on WANDR Benchmark — perplexity_ai · 2026-08-29
- Dev Comparison: Kimi K3 Beats Claude 5.6 in Kernel Tasks, Codex Leads in Debugging — YouJiacheng · 2026-08-29