# How do you score turn-taking smoothness when a user interrupts the agent?

With a dedicated grader on the turn itself, because a transcript-only eval can score every one of a caller's replies as accurate and still miss that the caller got talked over. IHBench, a 2026 benchmark on post-interruption recovery in voice agents, found GPT-family models correctly resume an utterance after a backchannel like "mm-hm" only 7% to 31% of the time, against 62% to 68% for Gemini 2.5. None of that shows up in the words: the resumed sentence still reads as a complete, plausible reply.

Grading it needs the trace to carry turn structure, who was speaking when, and where a backchannel or a real interruption landed inside an utterance. [Instrumentation](/answers/instrumentation/what-is-agent-instrumentation) that records only the final transcript has nothing for a turn-taking grader to read, which is a gap in what got captured, not something a better grader can work around.

Two things get graded separately: how fast the agent yields the floor, and whether it resumes at the right point afterward. An agent can do one well and still fail the other.

---

Sources:
- IHBench: Evaluating Post-Interruption Recovery in Voice Agents (arXiv:2606.19595): https://arxiv.org/abs/2606.19595 (fetched 2026-09-07)

Source: https://tessary.ai/answers/graders/grading-turn-taking-when-a-user-interrupts-the-agent
More on Graders: https://tessary.ai/answers/graders
From Tessary, agent reliability for AI agents in production: https://tessary.ai