Create README.md

README.md

@@ -0,0 +1,105 @@
+
+
+
+# Qwen3-Coder-30B-A3B-Instruct-FP8-Dynamic Evaluation Results
+
+## Open LLM Leaderboard Benchmark Performance
+
+| Benchmark | Score | Std Error |
+|---------|------|---------|
+| ARC Challenge (acc) | 65.36% | ±1.39% |
+| ARC Challenge (acc_norm) | 67.83% | ±1.37% |
+| GSM-8K (flexible-extract) | 89.84% | ±0.83% |
+| GSM-8K (strict-match) | 88.93% | ±0.86% |
+| Hellaswag (acc) | 50.25% | ±0.50% |
+| Hellaswag (acc_norm) | 58.75% | ±0.49% |
+| MMLU (overall) | 78.07% | ±0.33% |
+| TruthfulQA MC1 | 38.31% | ±1.70% |
+| TruthfulQA MC2 | 59.00% | ±1.64% |
+| Winogrande | 62.75% | ±1.36% |
+
+## MMLU Category Performance
+
+| Category | Score | Std Error |
+|---------|------|---------|
+| Humanities | 69.93% | ±0.64% |
+| Other | 79.95% | ±0.69% |
+| Social Sciences | 86.22% | ±0.61% |
+| STEM | 80.40% | ±0.69% |
+
+## Humanities Subcategory Performance
+
+| Subject | Score | Std Error |
+|------|------|---------|
+| Formal Logic | 61.90% | ±4.34% |
+| High School European History | 86.67% | ±2.65% |
+| High School US History | 86.76% | ±2.38% |
+| High School World History | 89.03% | ±2.03% |
+| International Law | 82.64% | ±3.46% |
+| Jurisprudence | 82.41% | ±3.68% |
+| Logical Fallacies | 82.21% | ±3.00% |
+| Moral Disputes | 74.86% | ±2.34% |
+| Moral Scenarios | 67.15% | ±1.57% |
+| Philosophy | 77.17% | ±2.38% |
+| Prehistory | 83.02% | ±2.09% |
+| Professional Law | 54.95% | ±1.27% |
+| World Religions | 85.38% | ±2.71% |
+
+## Social Sciences Subcategory Performance
+
+| Subject | Score | Std Error |
+|------|------|---------|
+| Econometrics | 72.81% | ±4.19% |
+| High School Geography | 90.40% | ±2.10% |
+| High School Government and Politics | 95.34% | ±1.52% |
+| High School Macroeconomics | 85.64% | ±1.78% |
+| High School Microeconomics | 91.60% | ±1.80% |
+| High School Psychology | 93.94% | ±1.02% |
+| Human Sexuality | 86.26% | ±3.02% |
+| Professional Psychology | 81.70% | ±1.56% |
+| Public Relations | 74.55% | ±4.17% |
+| Security Studies | 75.51% | ±2.75% |
+| Sociology | 85.57% | ±2.48% |
+| US Foreign Policy | 91.00% | ±2.88% |
+
+## STEM Subcategory Performance
+
+| Subject | Score | Std Error |
+|------|------|---------|
+| Abstract Algebra | 72.00% | ±4.51% |
+| Anatomy | 73.33% | ±3.82% |
+| Astronomy | 90.13% | ±2.43% |
+| College Biology | 89.58% | ±2.55% |
+| College Chemistry | 62.00% | ±4.88% |
+| College Computer Science | 79.00% | ±4.09% |
+| College Mathematics | 64.00% | ±4.82% |
+| College Physics | 72.55% | ±4.44% |
+| Computer Security | 86.00% | ±3.49% |
+| Conceptual Physics | 90.21% | ±1.94% |
+| Electrical Engineering | 80.69% | ±3.29% |
+| Elementary Mathematics | 85.45% | ±1.82% |
+| High School Biology | 92.90% | ±1.46% |
+| High School Chemistry | 77.83% | ±2.92% |
+| High School Computer Science | 86.00% | ±3.49% |
+| High School Mathematics | 66.67% | ±2.87% |
+| High School Physics | 75.50% | ±3.51% |
+| High School Statistics | 78.70% | ±2.79% |
+| Machine Learning | 75.89% | ±4.06% |
+
+## Other Subcategory Performance
+
+| Subject | Score | Std Error |
+|------|------|---------|
+| Business Ethics | 80.00% | ±4.02% |
+| Clinical Knowledge | 83.40% | ±2.29% |
+| College Medicine | 78.03% | ±3.16% |
+| Global Facts | 51.00% | ±5.02% |
+| Human Aging | 79.37% | ±2.72% |
+| Management | 85.44% | ±3.49% |
+| Marketing | 89.74% | ±1.99% |
+| Medical Genetics | 88.00% | ±3.27% |
+| Miscellaneous | 88.25% | ±1.15% |
+| Nutrition | 80.72% | ±2.26% |
+| Professional Accounting | 64.89% | ±2.85% |
+| Professional Medicine | 84.19% | ±2.22% |
+| Virology | 50.60% | ±3.89% |