Model Selection Evaluation on PRISM
93.2Actual Score (per type)Actual (per type)
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| Actual (per type)Setting=Pure capability2025.12 | 93.2 | — | — | — | — | — | |
| Actual (per type)Setting=Cost-aware (low)2025.12 | 25.2 | — | — | — | — | — | |
| Actual (per type)Setting=Constrained (single)2025.12 | 25.2 | — | — | — | — | — | |
| Actual (per type)Setting=Constrained (all)2025.12 | 25.2 | — | — | — | — | — | |
| Actual (per type)Setting=Cost-aware (high)2025.12 | -586 | — | — | — | — | — | |
| Actual (mean)Setting=Pure capability2025.12 | — | — | 93.2 | — | — | — | |
| Actual (mean)Setting=Cost-aware (low)2025.12 | — | — | 25.2 | — | — | — | |
| Actual (mean)Setting=Cost-aware (high)2025.12 | — | — | -586 | — | — | — | |
| Actual (mean)Setting=Constrained (single)2025.12 | — | — | 25.2 | — | — | — | |
| Actual (mean)Setting=Constrained (all)2025.12 | — | — | 25.2 | — | — | — | |
| BaselinesSetting=Pure capability2025.12 | — | — | — | — | — | 0.788 | |
| BaselinesSetting=Cost-aware (low)2025.12 | — | — | — | — | — | 0.46 | |
| BaselinesSetting=Cost-aware (high)2025.12 | — | — | — | — | — | -2.491 | |
| BaselinesSetting=Constrained (single)2025.12 | — | — | — | — | — | 0.46 | |
| BaselinesSetting=Constrained (all)2025.12 | — | — | — | — | — | 0.46 | |
| MLC (mean)Setting=Pure capability2025.12 | — | — | — | 81.9 | — | — | |
| MLC (mean)Setting=Cost-aware (low)2025.12 | — | — | — | 53.8 | — | — | |
| MLC (mean)Setting=Cost-aware (high)2025.12 | — | — | — | 46.5 | — | — | |
| MLC (mean)Setting=Constrained (single)2025.12 | — | — | — | 53.8 | — | — | |
| MLC (mean)Setting=Constrained (all)2025.12 | — | — | — | 53.8 | — | — | |
| MLC (per type)Setting=Pure capability2025.12 | — | 94.1 | — | — | — | — | |
| MLC (per type)Setting=Cost-aware (low)2025.12 | — | 46 | — | — | — | — | |
| MLC (per type)Setting=Cost-aware (high)2025.12 | — | 45 | — | — | — | — | |
| MLC (per type)Setting=Constrained (single)2025.12 | — | 45.4 | — | — | — | — | |
| MLC (per type)Setting=Constrained (all)2025.12 | — | 46.2 | — | — | — | — | |
| MLC (robust)Setting=Pure capability2025.12 | — | — | — | — | 75.2 | — | |
| MLC (robust)Setting=Cost-aware (low)2025.12 | — | — | — | — | 53.8 | — | |
| MLC (robust)Setting=Cost-aware (high)2025.12 | — | — | — | — | 46.5 | — | |
| MLC (robust)Setting=Constrained (single)2025.12 | — | — | — | — | 53.8 | — | |
| MLC (robust)Setting=Constrained (all)2025.12 | — | — | — | — | 53.8 | — |