sim_eval/eval_summary.md

# Sim eval — ep-0300 (Phase A screen (30 ep/task))

- **phase**: `Phase A screen (30 ep/task)`
- **mean_success_rate**: `0.39666666666666667`
- **n_test**: 300
- **n_test_per_task**: 30
- **test_start_seed**: 1000
- **num_exp**: 1

## Per-task SR

| Task | SR |
|------|-----|
| `KITCHEN_SCENE4_put_the_black_bowl_in_the_bottom_drawer_of_th` | 100.0% |
| `KITCHEN_SCENE3_turn_on_the_stove_and_put_the_moka_pot_on_it` | 83.3% |
| `KITCHEN_SCENE6_put_the_yellow_and_white_mug_in_the_microwave` | 83.3% |
| `LIVING_ROOM_SCENE5_put_the_white_mug_on_the_left_plate_and_p` | 46.7% |
| `KITCHEN_SCENE8_put_both_moka_pots_on_the_stove` | 33.3% |
| `LIVING_ROOM_SCENE2_put_both_the_cream_cheese_box_and_the_but` | 30.0% |
| `LIVING_ROOM_SCENE6_put_the_white_mug_on_the_plate_and_put_th` | 20.0% |
| `LIVING_ROOM_SCENE1_put_both_the_alphabet_soup_and_the_cream_` | 0.0% |
| `LIVING_ROOM_SCENE2_put_both_the_alphabet_soup_and_the_tomato` | 0.0% |
| `STUDY_SCENE1_pick_up_the_book_and_place_it_in_the_back_compa` | 0.0% |