Math & Science on GSM8K (test)
90.2AccuracyWeDLM-8B
Evaluation Results
| Method | Links | |
|---|---|---|
| WeDLM-8BModel Type=WeDLM (Ours), Base Model=Qwen3-8B, Few-shot setting=3-shot2025.12 | 90.2 | |
| Qwen3-8BModel Type=AR Baseline, Few-shot setting=3-shot2025.12 | 85.97 | |
| WeDLM-7BModel Type=WeDLM (Ours), Base Model=Qwen2.5-7B, Few-shot setting=3-shot2025.12 | 84.76 | |
| Qwen2.5-7BModel Type=AR Baseline, Few-shot setting=3-shot2025.12 | 79.23 | |
| Dream-7BModel Type=DLLM Baseline, Few-shot setting=3-shot2025.12 | 75.97 | |
| LLaDA-8BModel Type=DLLM Baseline, Few-shot setting=3-shot2025.12 | 71.8 |