Polish: distinguish wild-mode (~44%) vs benchmark-mode (~56%) gap recovery

Per auditor feedback: the previous '56% of the gap' line was the
benchmark-mode number; spell out both modes' recovery fractions to
avoid ambiguity for readers who skim the lede.

README.md

@@ -26,9 +26,10 @@ modified** — this method ships a CLIP-ViT-L/14-driven frame selector
 plus an optional task-type-aware uniform-fallback policy as a
 wrapper around the stock model.
 
-On Video-MME mini at 8-frame budget, this recovers **56 % of the
-8-frame → 64-frame stock baseline gap with zero training, zero
-parameter changes, and ~+0.4 s overhead per question**.
+On Video-MME mini at 8-frame budget, this recovers **~44 % of the
+8-frame → 64-frame stock baseline gap in wild mode, and ~56 % in
+benchmark mode**, with zero training, zero parameter changes, and
+~+0.4 s overhead per question.
 
 ## TL;DR