Multi-task Agent Execution on HiMA-Ecom (test)
98Math Score
DeepSeek-R1
Updated 17d ago
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
2025.06 | 98 | 34.7 | 19.3 | 72.4 | 5.3 | 45.9 | |
2025.06 | 95.7 | 32.3 | 6.3 | 77.2 | 3 | 42.9 | |
2025.06 | 84.3 | 35 | 50.3 | 76.2 | 5 | 50.2 | |
2025.06 | 80 | 30.3 | 0.3 | 43 | 2 | 31.2 | |
2025.06 | 71 | 34.2 | 3 | 68.9 | 1.7 | 35.8 | |
2025.06 | 70 | 20.7 | 48.3 | 73.9 | 7 | 44 | |
2025.06 | 65 | 19.3 | 39.3 | 63.5 | 5 | 38.4 |