Large Model Performance Prediction (v1.0, 40% masking)
6.13RMSESTAR
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| STARMethod Category=LLM-based Methods2026.02 | 6.13 | 3.98 | 5.06 | 97.65 | 91.73 | 77.83 | 89.07 | 84.01 | |
| Semantic-Augmented CPMFMethod Category=LLM-based Methods2026.02 | 6.38 | 4.33 | 5.36 | 97.47 | 91.27 | 76.38 | 88.37 | 83.01 | |
| PMFMethod Category=Statistic-based Methods2026.02 | 7.17 | 5.03 | 6.1 | 96.89 | 89.89 | 76.17 | 87.65 | 81.55 | |
| PCAMethod Category=Statistic-based Methods2026.02 | 11.53 | 7.28 | 9.41 | 93.22 | 85.19 | 63.77 | 80.73 | 71.32 | |
| RegressionMethod Category=Statistic-based Methods2026.02 | 11.66 | 7.28 | 9.47 | 92.6 | 85.32 | 67.55 | 81.82 | 72.35 | |
| Mean Of MeansMethod Category=Statistical Baselines2026.02 | 12.87 | 9.46 | 11.17 | 91.83 | 83.65 | 74.24 | 83.24 | 72.07 | |
| NCFMethod Category=Statistic-based Methods2026.02 | 13.58 | 8.91 | 11.25 | 90.17 | 81.61 | 46.38 | 72.72 | 61.47 | |
| LLM-RAGMethod Category=LLM-based Methods2026.02 | 13.93 | 7.93 | 10.93 | 81.71 | 66.9 | 53.62 | 67.41 | 56.48 | |
| Global MeanMethod Category=Statistical Baselines2026.02 | 16.03 | 12.51 | 14.27 | 83.79 | 75.46 | 23.51 | 60.92 | 46.65 | |
| Pure LLMMethod Category=LLM-based Methods2026.02 | 23.6 | 16.43 | 20.02 | 72.47 | 66.88 | 24.89 | 54.75 | 34.73 |