General Performance Averaging on Consolidated Task Suite Avg.
77.6Average Accuracy
Primitives-based MAS
Updated 12d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.02 | 77.6 | 12 | |
2026.02 | 74.3 | 8.8 | |
2026.02 | 73.7 | 8.1 | |
2026.02 | 73 | 7.4 | |
2026.02 | 72.6 | 7.1 | |
2026.02 | 71.4 | 5.9 | |
2026.03 | 70.1 | - | |
2026.02 | 69.6 | 13.9 | |
2026.02 | 66 | 10.3 | |
2026.02 | 65.5 | - | |
2026.02 | 64.5 | 8.8 | |
2026.02 | 63.1 | 7.4 | |
2026.02 | 62.1 | 6.4 | |
2026.02 | 61.3 | 5.6 | |
2026.03 | 58.1 | - | |
2026.03 | 57.8 | - | |
2026.02 | 55.7 | - | |
2026.03 | 51.7 | - | |
2026.03 | 50 | - | |
2026.03 | 49.6 | - | |
2026.03 | 49.1 | - | |
2026.03 | 42.7 | - | |
2026.03 | 35.8 | - |