Code Generation on HumanEval 4-shot
80.49ScoreWeDLM-8B
Evaluation Results
| Method | Links | |
|---|---|---|
| WeDLM-8BInstruct Model=true, Model Category=WeDLM, Shot Configuration=4-shot, Inference Framework=vLLM, Sampling Temperature=0.1, Max Generation Length=512, Window Size (W)=6, Penalty Coefficient (λ)=0.12025.12 | 80.49 | |
| SDAR-8BInstruct Model=true, Model Category=DLLM Baseline, Shot Configuration=4-shot, Inference Framework=JetEngine, Sampling Temperature=0.1, Max Generation Length=512, Window Size (W)=6, Penalty Coefficient (λ)=0.12025.12 | 76.83 | |
| Qwen2.5-7BInstruct Model=true, Model Category=AR Baseline, Shot Configuration=4-shot, Inference Framework=vLLM, Sampling Temperature=0.1, Max Generation Length=5122025.12 | 76.22 | |
| WeDLM-7BInstruct Model=true, Model Category=WeDLM, Shot Configuration=4-shot, Inference Framework=vLLM, Sampling Temperature=0.1, Max Generation Length=512, Window Size (W)=6, Penalty Coefficient (λ)=0.12025.12 | 75 | |
| Qwen3-8BInstruct Model=true, Model Category=AR Baseline, Shot Configuration=4-shot, Inference Framework=vLLM, Sampling Temperature=0.1, Max Generation Length=5122025.12 | 71.95 | |
| Dream-7BInstruct Model=true, Model Category=DLLM Baseline, Shot Configuration=4-shot, Inference Framework=dInfer, Sampling Temperature=0.1, Max Generation Length=512, Window Size (W)=6, Penalty Coefficient (λ)=0.12025.12 | 57.32 | |
| LLaDA-8BInstruct Model=true, Model Category=DLLM Baseline, Shot Configuration=4-shot, Inference Framework=dInfer, Sampling Temperature=0.1, Max Generation Length=512, Window Size (W)=6, Penalty Coefficient (λ)=0.12025.12 | 36.59 |