Toast Bread on Real-World Tasks Toast Bread
81Success RateTACO
Evaluation results
| Method | Links | ||
|---|---|---|---|
| TACOIteration=22026.07 | 81 | 177 | |
| TACOIteration=12026.07 | 70 | 184 | |
| TACO (w/o KI)Iteration=22026.07 | 51 | 191 | |
| TACO (w/o KI)Iteration=12026.07 | 48 | 193 | |
| Filtered BCIteration=22026.07 | 36 | 177 | |
| Filtered BCIteration=12026.07 | 32 | 189 | |
| Base PolicyIteration=Base2026.07 | 30 | 183 |