Education
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Safety and Utility Evaluation | Education subset | JSR80.4 | 44 | |
| Predictive Modeling across Groups | Education | RWA0.946 | 24 | |
| Regression | Education | MSE0.15 | 24 | |
| Privacy appropriateness classification | Education | F1 (Area)84.8 | 20 | |
| Node-level Regression Uncertainty Quantification | Education | PICP100 | 10 | |
| Uncertainty Quantification | Education | MPE0.09 | 9 | |
| Uncertainty Quantification | Education | Sharpness0.01 | 9 | |
| Marginal Prediction Length | Education (EDU) | Marginal Prediction Length1.88 | 6 | |
| Trend Alignment | Education | ∆Bias0.0716 | 6 | |
| Downstream classification | Education Unconstrained | F1 Score44.9 | 4 | |
| Human Evaluation | Education subset | Win Rate85 | 3 | |
| Idea Generation | Education | Ideas Accepted1,000 | 3 | |
| Downstream classification | Education Category-controlled top-K | F1 Score83.8 | 3 |
Showing 13 of 13 rows