Knowledge Reasoning on GPQA Diamond (Score)
37.3ScoreExpertWeaver
Evaluation results
| Method | Links | |
|---|---|---|
| ExpertWeaverBase Model=DeepSeek-R1-Distill-Qwen-7B, Sparsity=12.5%2026.02 | 37.3 | |
| FLAPBase Model=DeepSeek-R1-Distill-Qwen-7B, Sparsity=12.5%2026.02 | 36.3 | |
| LLM-PrunerBase Model=DeepSeek-R1-Distill-Qwen-7B, Sparsity=12.5%2026.02 | 33.3 |