Model-Query Evaluation
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Correctness Prediction | Model-Query Evaluation (112 language models, 10 public benchmarks) (test) | Accuracy (Prediction)70.12 | 9 | |
| Model Routing | Model-Query Evaluation (test) | Routing Accuracy (%)64.7 | 9 |
Showing 2 of 2 rows