Scaling Model Validation on BrowseComp-Plus Out-of-sample (val)
0.071MAE
predictive framework for agentic scaling
Updated 4d ago
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| 0.071 | 15.8 | 0.045 | - | 0.2 |
predictive framework for agentic scaling
| Method | Links | |||||
|---|---|---|---|---|---|---|
| 0.071 | 15.8 | 0.045 | - | 0.2 |