Update README.md

README.md

@@ -89,13 +89,6 @@ Held-out validation split (9,495 rows, 107 labels):
 | macro F1 | **0.9206** |
 | accuracy | 0.9306 |
 
-Head-to-head vs `philomath-1209/programming-language-identification` on the 26
-labels both models support (3,057 test rows):
-
-| model | accuracy | macro F1 |
-|---|---|---|
-| **this model** | **0.9444** | **0.9636** |
-| philomath-1209 | 0.8449 | 0.8445 |
 
 Wins on every shared label. Largest gaps: ARM Assembly +0.354, Erlang +0.270,
 COBOL +0.216, Pascal +0.206, Fortran +0.193, Mathematica/Wolfram +0.173.