Math & Science on GPQA Diamond (test)
42.42ScoreWeDLM-8B
Evaluation Results
| Method | Links | |
|---|---|---|
| WeDLM-8BModel Type=WeDLM (Ours), Base Model=Qwen3-8B, Few-shot setting=5-shot2025.12 | 42.42 | |
| Qwen3-8BModel Type=AR Baseline, Few-shot setting=5-shot2025.12 | 37 | |
| WeDLM-7BModel Type=WeDLM (Ours), Base Model=Qwen2.5-7B, Few-shot setting=5-shot2025.12 | 36.87 | |
| Qwen2.5-7BModel Type=AR Baseline, Few-shot setting=5-shot2025.12 | 33.7 | |
| LLaDA-8BModel Type=DLLM Baseline, Few-shot setting=5-shot2025.12 | 29.8 | |
| Dream-7BModel Type=DLLM Baseline, Few-shot setting=5-shot2025.12 | 25.76 |