General Reasoning on ARC Challenge (test)
92.92ScoreWeDLM-8B
Evaluation Results
| Method | Links | |
|---|---|---|
| WeDLM-8BModel Type=WeDLM (Ours), Base Model=Qwen3-8B, Few-shot setting=0-shot2025.12 | 92.92 | |
| Qwen3-8BModel Type=AR Baseline, Few-shot setting=0-shot2025.12 | 92.66 | |
| WeDLM-7BModel Type=WeDLM (Ours), Base Model=Qwen2.5-7B, Few-shot setting=0-shot2025.12 | 90.7 | |
| Qwen2.5-7BModel Type=AR Baseline, Few-shot setting=0-shot2025.12 | 89.93 | |
| Dream-7BModel Type=DLLM Baseline, Few-shot setting=0-shot2025.12 | 88.4 | |
| LLaDA-8BModel Type=DLLM Baseline, Few-shot setting=0-shot2025.12 | 81.14 |