OpenYap Turn tops Sesame's TurnBench trained only on real friend-and-family conversations
realmrfakename · x · 2026-10-18
The Agentic Data Company's OpenYap Turn ranks #1 of 24 on end-of-turn prediction (recall 0.978, 298ms median latency) and #2 of 23 on interruption on Sesame's TurnBench.
Their thesis: most "natural" conversational speech datasets consist of paired strangers given a topic, which strips out exactly the overlap, interruptions, and silences that teach a model how real conversations are structured. Trained on 1,984 hours of genuine conversations between friends and family, the model tops the leaderboard.
Notably, the team argues such small turn-taking models are not the answer, and closes with their reasoning.
More from Research
- Periodic's CoLM talk: when does training your own model beat frontier + harness? — heghbalz · 2026-10-18
- PNAS paper shows biological synapses can self-assemble learning rules akin to gradient descent — xuanalogue · 2026-10-18
- SGPnP paper accepted at IEEE TCI: diffusion priors plug into PnP reconstruction with theory — prof_kamilov · 2026-10-18
- Surya Ganguli lecture traces the statistical-physics origins of scaling laws — burny_tech · 2026-10-18
- Domingos: superposition is a feature, not a bug — it boosts memory, not blocks interpretability — pmddomingos · 2026-10-18
- AMI-EV: spinning prism gives event cameras stable texture, Science Robotics 2024 — RexDouglass · 2026-10-18