Update README.md

README.md

@@ -148,20 +148,20 @@ The loss curve demonstrates stable convergence with the final training loss reac
 
 | **Benchmark** | **Metric** | **Base Gemma-3-27B-IT** | **LogicFlow-Gemma-3-27b-thinking** | **Improvement** |
 |---------------|------------|--------------------------|-------------------------------------|-----------------|
-| ** Mathematical Reasoning** |
+| **Mathematical Reasoning** |
 | GSM8K | Exact Match | 82.6% | **89.5%** | **+6.9%** |
 | MATH | Accuracy | 50.0% | **76.8%** | **+26.8%** |
-| ** Code Generation** |
+| **Code Generation** |
 | MBPP | pass@1 | 65.6% | **69.0%** | **+3.4%** |
 | HumanEval | 0-shot | 48.8% | *Pending* | *TBD* |
-| ** Instruction Following** |
+| **Instruction Following** |
 | IFEval | Prompt-level | *45.0%* | **40.0%** | **-5.0%** |
 | IFEval | Instruction-level | *58.0%* | **53.1%** | **-4.9%** |
-| ** Advanced Mathematics** |
+| **Advanced Mathematics** |
 | AIME25 | Problem Solving | ~8-12% | **13.3%** | **+1-5%** |
-| ** Scientific Reasoning** |
+| **Scientific Reasoning** |
 | GPQA Diamond | Science QA | ~30-35% | **45.96%** | **+11-16%** |
-| ** Knowledge & Understanding** |
+| **Knowledge & Understanding** |
 | MMLU | Overall Accuracy | 78.6% | **75.3%** | **-3.3%** |
 | MMLU STEM | Sciences & Math | ~70.0% | **71.6%** | **+1.6%** |
 | MMLU Humanities | Arts & Literature | ~67.0% | **69.2%** | **+2.2%** |
@@ -422,10 +422,10 @@ The model showcases systematic thinking through:
 - Clear documentation of the reasoning process
 
 These examples demonstrate the model's ability to:
-- ** Break down complex problems** into manageable steps
-- ** Self-verify results** using multiple approaches  
-- ** Document reasoning chains** for transparency
-- ** Maintain accuracy** while showing work
+- **Break down complex problems** into manageable steps
+- **Self-verify results** using multiple approaches  
+- **Document reasoning chains** for transparency
+- **Maintain accuracy** while showing work
 
 ### Activating Chain-of-Thought Reasoning