diff --git a/docs/ROADMAP.md b/docs/ROADMAP.md
index 7218d32..7445f87 100644
--- a/docs/ROADMAP.md
+++ b/docs/ROADMAP.md
@@ -78,9 +78,12 @@ release should not go out without.
    while decoding, and the image loader's caches are decided explicitly — memory only at 15 % of the heap,
    no disk cache. The device pass is in [EDGE_CASE_TESTING](EDGE_CASE_TESTING.md): 6 200 files with 300
    images and a folder of 300 images, correct and stable, no crash or OOM. A 20 000-*image* folder is
-   still unmeasured, and jank on this screen needs a device that reports frame durations.
-3. **The scaling numbers** — `./tools/benchmark-fixture.sh --count 20000` and the existing benchmarks:
-   answers whether a full SD card is a performance problem before a user with one finds out.
+   still unmeasured; jank on the screen is measurable now that both the phone run and the CI emulator
+   report `frameDurationCpuMs` (see [PERFORMANCE](PERFORMANCE.md)), but no test drives the photo grid yet.
+3. **The scaling numbers** — **done**: 1 000 → 12–14 frames to open, 5 000 → 41, 20 000 → 184 with a 598
+   outlier; the outlier was investigated and the real fix was progressive listing (200-entry batches,
+   O(n+k) merge), after which 20 000 files opens in **10–16 frames** with a 32–48 max across two runs. The
+   whole suite at that size, and what search costs there, is in [PERFORMANCE](PERFORMANCE.md).
 4. **Copy to… / Move to… (M16)** — **done**: the selection bar's overflow opens a folder picker (volumes,
    then folders one level at a time, Up and the trail above them) and confirming copies or moves into the
    picked folder without leaving the current one. The selection survives a copy so a second destination is