Procedural Temporal Understanding on LEGO-Puzzles (test)
42.82Overall Accuracy
TPRU-7B
Updated 5mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.02 | 42.82 | 3,200 | |
2026.02 | 41.64 | 500 | |
2026.02 | 36.45 | 1,200 | |
2026.02 | 34.45 | 200 | |
2026.02 | 31.91 | 100 | |
2026.02 | 28.18 | 0 | |
2026.02 | 27.27 | 0 |