Agent tool-use planning on GeoScenario 9 Tools 116 (test)
73.8TSA
Qwen3-8B
Updated 27d ago
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
2026.05 | 73.8 | 73.5 | 53.1 | 30.2 | 87.9 | 83.5 | 61.7 | |
2026.05 | 68.5 | 68.5 | 54.7 | 35.6 | 96.6 | 91.7 | 76 | |
2026.05 | 66.8 | 66.3 | 49.1 | 36.5 | 97 | 92.3 | 52.2 | |
2026.05 | 46.1 | 45.9 | 37.9 | 39.9 | 72.2 | 69 | 48.6 | |
2026.05 | 41.6 | 40.4 | 31.5 | 39.1 | 65.5 | 56.4 | 20.4 | |
2026.05 | 34.8 | 34.7 | 26.5 | 38.3 | 56 | 48.7 | 21.4 |