Clarify perf lower bound for FT/GIL

Author: Fidget-Spinner

peps/pep-0836.rst

@@ -79,8 +79,10 @@ At a high level, these are our milestones and goals for the JIT over the next
     JIT stencils, without requiring long-term dependence on one exact LLVM
     version [#community-perspectives]_.
 
-  * **No lower than 5% uplift on the JIT versus the interpreter on the mean of
-    our supported platforms after implementing the above changes.** In other
+  * **No lower than 4% uplift on the JIT + free-threading versus
+    the free-threading interpreter on the mean of our supported platforms
+    after implementing the above changes.** Additionally, no lower than 5%
+    uplift on the JIT + GIL build versus the GIL interpreter. In other
     words, we will not significantly regress base performance improvements
     while in pursuit of longer-term goals. We will also not discourage other
     contributors from contributing performance improvements during this stage.
@@ -89,7 +91,7 @@ At a high level, these are our milestones and goals for the JIT over the next
 * **Year 2 (ending with Python 3.17's first beta) - Improved performance**
 
   * **Achieve at least 20% performance geometric mean improvement on
-    pyperformance for JIT + free-threading compared to free-threading
+    pyperformance for JIT + free-threading compared to the free-threading
     interpreter alone.** This is the minimum target for keeping the JIT in
     CPython main, with free-threading treated as the primary performance focus.