LLM Performance Estimation on Winogrande (test)
1.027MAESparseEval
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| SparseEvalNumber of Anchors=1002026.02 | 1.027 | 0.897 | |
| SparseEvalNumber of Anchors=802026.02 | 1.182 | 0.882 | |
| SparseEvalNumber of Anchors=602026.02 | 1.361 | 0.867 | |
| SparseEvalNumber of Anchors=402026.02 | 1.5 | 0.853 | |
| gp-IRTNumber of Anchors=1002026.02 | 1.957 | 0.725 | |
| SparseEvalNumber of Anchors=202026.02 | 2.088 | 0.794 | |
| gp-IRTNumber of Anchors=802026.02 | 2.284 | 0.659 | |
| gp-IRTNumber of Anchors=602026.02 | 2.617 | 0.63 | |
| Anchor PointsNumber of Anchors=1002026.02 | 3.019 | 0.81 | |
| TailoredBenchNumber of Anchors=1002026.02 | 3.12 | 0.788 | |
| TailoredBenchNumber of Anchors=802026.02 | 3.13 | 0.752 | |
| TailoredBenchNumber of Anchors=202026.02 | 3.212 | 0.705 | |
| gp-IRTNumber of Anchors=402026.02 | 3.417 | 0.547 | |
| TailoredBenchNumber of Anchors=602026.02 | 3.478 | 0.76 | |
| Anchor PointsNumber of Anchors=802026.02 | 3.621 | 0.752 | |
| TailoredBenchNumber of Anchors=402026.02 | 3.74 | 0.751 | |
| Anchor PointsNumber of Anchors=402026.02 | 4.037 | 0.737 | |
| Anchor PointsNumber of Anchors=602026.02 | 4.038 | 0.71 | |
| gp-IRTNumber of Anchors=202026.02 | 4.903 | 0.533 | |
| Anchor PointsNumber of Anchors=202026.02 | 5.577 | 0.694 |