Update README.md

README.md

@@ -41,7 +41,7 @@ NSQL-llama-2-7B was evaluated on the Spider benchmark, the standard academic eva
 
 | Model | Size | Execution Accuracy | Matching Accuracy |
 |-------|------|-------------------|-------------------|
-| **NSQL-llama-2-7B** | 7B | 75.0% | **66.3%** |
+| **NSQL-llama-2-7B** | 7B | 78.1% | **66.3%** |
 | GPT-4 | ~1.8T | 76.2% | 41.9% |
 | GPT-3.5 Chat | — | 72.8% | 44.2% |
 | Llama-2-7B (base) | 7B | 29.1% | 19.3% |
@@ -63,7 +63,7 @@ NSQL-llama-2-7B was evaluated on the Spider benchmark, the standard academic eva
 
 2. **Matching Accuracy:** NSQL achieves 66.3% matching accuracy vs. GPT-4's 41.9% (+24.4 points), indicating more structurally correct SQL generation.
 
-3. **Efficiency:** NSQL achieves near-parity with GPT-4 on overall execution (75.0% vs 76.2%) while being ~250× smaller.
+3. **Efficiency:** NSQL achieves near-parity with GPT-4 on overall execution (78.10% vs 76.2%) while being ~250× smaller.
 
 4. **Local Deployment:** The 7B parameter size enables local deployment on commodity hardware, preserving data privacy.
 
@@ -92,7 +92,7 @@ On these complex query types, NSQL substantially outperforms GPT-4 while enablin
 | NSQL-350M | 350M | 51.7% | 45.6% |
 | NSQL-2B | 2B | 59.3% | 53.2% |
 | NSQL-6B | 6B | 63.6% | 57.4% |
-| **NSQL-llama-2-7B** | **7B** | **75.0%** | **66.3%** |
+| **NSQL-llama-2-7B** | **7B** | **78.1%** | **66.3%** |
 
 ---