| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Runtime Speed | Qwen3 Query Projection Module | Throughput (k tokens/sec)92.57 | 90 | |
| Language Modeling | Qwen3 (val) | Validation Loss2.493 | 49 | |
| Large Language Model Evaluation | Qwen3-0.6B Average (test) | Average Performance47.83 | 38 | |
| Output Equivalence | Qwen3 | Exact Match65.6 | 13 | |
| LLM Inference | Qwen3 Samsung Galaxy S25 Ultra 0.6B (test) | Prefill Throughput (min)1,709.9 | 12 | |
| Long-Context Generation | Qwen3 Context length (60K) | Throughput Speedup (α)5.89 | 12 | |
| Long-Context Generation | Qwen3 Context length 40K | Throughput Speedup (α)5.37 | 12 | |
| Long-Context Generation | Qwen3 Context length 30K | Throughput Speedup (α)4.37 | 12 | |
| Long-Context Generation | Qwen3 Context length 20K | Throughput Speedup (α)3.73 | 12 | |
| LLM Inference | Qwen3 Google Pixel 9 Pro XL 0.6B (test) | Prefill Throughput (min, tokens/sec)591.01 | 10 | |
| Data Selection | QWEN3-4B | Wall-clock Time1 | 8 | |
| Training Throughput | Qwen3-30B-A3B workload | Throughput (tokens/s)280,000 | 7 | |
| Kernel-level Attention Speed and Memory Analysis | Qwen3-8B model dimensions (H=32, Hk=8, d=128, GQA 4:1) on A100 GPU (test) | Forward Pass Time (ms)27.1 | 7 | |
| Watermark Removal | Qwen3 8B | DIPMark14.21 | 6 | |
| Model Merging | Qwen3-4B-Base Transfer 8 benchmarks | Math Accuracy32.65 | 6 | |
| Training Throughput | Qwen3 32B (train) | Training Throughput (128K Seq Len)545.29 | 5 | |
| LLM Jailbreaking | Qwen3 4B Instruct 2507 | SRF71 | 4 | |
| Hybrid-Dimension Reconfiguration | Qwen3-30B-A3B | Reconfiguration Time (s)0.42 | 4 | |
| Language Modeling | Qwen3-0.6B (val) | Validation Perplexity31.45 | 3 | |
| vLLM Model Deployment and Inference | Qwen3-32B inference vLLM | Model Load Time (s)7.641 | 3 | |
| vLLM Model Deployment and Inference | Qwen3-14B vLLM (inference) | Model Load Time (s)3.082 | 3 | |
| vLLM Model Deployment and Inference | Qwen3-1.7B vLLM (inference) | Model Load Time (s)0.54 | 3 | |
| Optimizer state memory measurement | Qwen3-32B (train) | Optimizer State Memory (MB)125.9 | 2 | |
| Optimizer state memory measurement | Qwen3-30B-A3B (train) | Optimizer State Memory (MB)111.4 | 2 |