# Researchers show saturated benchmarks still carry capability signal in transcripts, and a live-clock test reverses model rankings

Pairwise judging of saturated transcripts cut capability-prediction error 5.3-fold, while RealtimeBench found that GPT-6.1-sol loses to a faster model once games keep running during inference.

- Published: 2026-10-16T06:26:08.965Z
- Canonical: https://polylog.news/ai/2026-10-16/researchers-show-saturated-benchmarks-still-carry-capability
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [arXiv cs.AI](https://arxiv.org/abs/2610.20667), [arXiv cs.AI](https://arxiv.org/abs/2610.20665)

Two new arXiv papers address the same problem: leaderboard scores no longer separate frontier models, or separate them in ways that do not match deployment. The first, "Evaluating Model Capabilities After Benchmark Saturation" by Morio Hama…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-10-16/researchers-show-saturated-benchmarks-still-carry-capability (subscription information: https://polylog.news/pricing).