General LLM Benchmarking on LiveBench
49.6Official ScoreSCAS
Evaluation Results
| Method | Links | |
|---|---|---|
| SCASModel=Qwen2.5-7B2026.05 | 49.6 | |
| RSR-ItemModel=Qwen2.5-7B2026.05 | 48.4 | |
| IFDModel=Qwen2.5-7B2026.05 | 47.9 | |
| PPLModel=Qwen2.5-7B2026.05 | 47.8 | |
| InfluenceModel=Qwen2.5-7B2026.05 | 47.6 | |
| GRACEModel=Qwen2.5-7B2026.05 | 47.5 | |
| RSRModel=Qwen2.5-7B2026.05 | 47.4 | |
| RouterModel=Qwen2.5-7B2026.05 | 47.1 | |
| GRACEModel=Qwen2.5-3B2026.05 | 42.3 | |
| SCASModel=Qwen2.5-3B2026.05 | 42.3 | |
| RSRModel=Qwen2.5-3B2026.05 | 42.2 | |
| RouterModel=Qwen2.5-3B2026.05 | 41.7 | |
| RSR-ItemModel=Qwen2.5-3B2026.05 | 41.6 | |
| IFDModel=Qwen2.5-3B2026.05 | 41.6 | |
| InfluenceModel=Qwen2.5-3B2026.05 | 41.6 | |
| PPLModel=Qwen2.5-3B2026.05 | 39.9 | |
| SCASModel=Qwen2.5-0.5B2026.05 | 27.2 | |
| IFDModel=Qwen2.5-0.5B2026.05 | 27.1 | |
| GRACEModel=Qwen2.5-0.5B2026.05 | 26.9 | |
| InfluenceModel=Qwen2.5-0.5B2026.05 | 26.9 | |
| RSR-ItemModel=Qwen2.5-0.5B2026.05 | 26.8 | |
| RouterModel=Qwen2.5-0.5B2026.05 | 26.7 | |
| PPLModel=Qwen2.5-0.5B2026.05 | 26.3 | |
| RSRModel=Qwen2.5-0.5B2026.05 | 24.3 |