Update README.md

README.md

@@ -25,7 +25,7 @@ It achieves **43–48% accuracy** on Rust-specific benchmarks – surpassing muc
 - **Peer-validated synthetic dataset** (191,008 verified examples, 94.3% compile rate)  
 - **LoRA-based fine-tuning** for efficient adaptation  
 - **Benchmarked across Rust-specific suites:**
-  - **RustEvo²**  
+  - **RustEvo^2**  
   - **Evaluation on Hold-Out Set**
 - **Deployed in the Fortytwo decentralized inference network** for collective AI reasoning  
 
@@ -33,7 +33,7 @@ It achieves **43–48% accuracy** on Rust-specific benchmarks – surpassing muc
 
 ## Performance Summary
 
-| **Model** | **Hold-Out Set** | **RustEvo²** |
+| **Model** | **Hold-Out Set** | **RustEvo^2** |
 |------------|------------------|---------------|
 | **Fortytwo-Rust-One-14B (Ours)** | **48.00%** | **43.00%** |
 | openai/gpt-5-codex | 47.00% | 28.00% |