VecEval
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Explanation Generation | VecEval (val) | B Score93.26 | 9 | |
| Context-aware Evaluation | VecEval (val) | Lingo-Judge Accuracy78.61 | 9 | |
| Urgency Prediction | VecEval (val) | Intervention Failure Rate12.12 | 9 |
Showing 3 of 3 rows