# RealtimeBench shows a slower frontier model losing to a faster one once the game clock keeps running

The paper's teacher-student method raises the fast model's score from 13.51 to 24.19 out of 100 without calling the slow model during play.

- Published: 2026-10-17T06:12:13.157Z
- Canonical: https://polylog.news/ai/2026-10-17/realtimebench-shows-a-slower-frontier-model-losing-to-a-fast
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [arXiv cs.AI](https://arxiv.org/abs/2610.20665), [arXiv (HTML)](https://arxiv.org/html/2610.20665)

Most agent benchmarks pause the environment while the model generates its response. A new paper, "The World Won't Wait", removes the pause. Its RealtimeBench contains 180 tasks across six game types. Under its live-clock protocol, the game…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-10-17/realtimebench-shows-a-slower-frontier-model-losing-to-a-fast (subscription information: https://polylog.news/pricing).