Update README.md

README.md

@@ -124,16 +124,9 @@ The model was fine-tuned on **82,000** high-value private samples:
 
 ## 6. 🏆 Performance Benchmarks
 
-Evaluated on **Web3-Finance-Eval-2026**:
+Evaluated on three key benchmarks: DMind Benchmark (Web3 Native Logic), FinanceQA (Financial Domain Knowledge), and AIME 2025 (Advanced Mathematical Reasoning).
 
-| Metric | DMind-3-mini (4B) | Llama-3-70B | GPT-4o (General) |
-| :--- | :---: | :---: | :---: |
-| **Ponzi Logic Detection** | **96.4%** | 78.2% | 85.5% |
-| **Impermanent Loss Calc** | **99.1%** | 85.0% | 92.3% |
-| **Contract Exploit ID** | **92.3%** | 88.5% | 89.1% |
-| **Inference Cost** | **Local (Free)** | High | High |
-
-*DMind-3-mini outperforms generalist models 15x its size in specific vertical tasks, validating the C³-SFT approach.*
+The evaluation compares DMind-3-mini (4B) against top-tier frontier models (GPT-5.1, Claude Sonnet 4.5) and other efficient models. Despite its compact size, the Mini model demonstrates exceptional efficiency, particularly in specialized domain tasks where it outperforms significantly larger generalist models.
 
 ## 7. ⚖️ Limitations & Disclaimer