Model Ranking on GovReport ROUGE-L (test)
0.823Kendall Tau (τ)Baseline
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| BaselineRanking Strategy=Baseline2026.01 | 0.823 | — | — | |
| Adaptive Multi-Model RankingRanking Strategy=Adaptive2026.01 | 0.8 | 98 | 0.025 |
Loading the SOTA2 catalog…