WorkloadBenchDataFollow @BrenBuilds on X

Rechecks

When posts say a model got worse or better, I run the same tests again and compare them with its earlier runs.

  1. 21 October 2026

    Claude Opus 5.5, rechecked after posts said it got worse

    Same hidden-test scores as before, though one bug-hunt run failed its gate. On the bug hunt and tickets tests it used 33% and 44% of its earlier thinking tokens.

  2. 12 October 2026

    GPT-6.1 Sol, rechecked after posts said it got better

    Same hidden-test scores as before. Every real-app measure overlapped its earlier range.

  3. 29 September to 6 October 2026

    GPT-6.1 Sol speed, timed day by day

    Every GPT-6.1 Sol run from 5 October's retest to 6 October streamed more text pieces a second than every run in the eight earlier sittings. Five of the twelve runs from 5 October's retest to 6 October finished inside launch day's 10.7 to 12.8 s; one finished sooner and six took longer.