Mathematical Reasoning on GSM8K, MATH, MATH500, OlympiadBench
82.94GSM8KHSA-UL-Inst
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| HSA-UL-InstArchitecture=MoE, Total Parameters=8B, Activated Parameters=1B, Training Tokens=8T, Supervised fine-tuning=true2025.11 | 82.94 | 61.56 | 71 | 27.85 | |
| Qwen3-InstArchitecture=Dense, Total Parameters=1.7B, Activated Parameters=1.7B, Training Tokens=36T, Supervised fine-tuning=true2025.11 | 79 | 64.32 | 73.2 | 36.3 | |
| Qwen3-InstArchitecture=Dense, Total Parameters=0.6B, Activated Parameters=0.6B, Training Tokens=36T, Supervised fine-tuning=true2025.11 | 55.65 | 45.26 | 53 | 16.89 | |
| HSA-UL-InstArchitecture=Dense, Total Parameters=0.5B, Activated Parameters=0.5B, Training Tokens=4T, Supervised fine-tuning=true2025.11 | 55.42 | 40.76 | 41 | 8.74 |