| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| ThinkGeo 14 Tools (test) | Qwen3-235B | Tool Selection Accuracy (TSA)77.7 | 8 | 27d ago | |
| EarthBench 104 Tools (test) | Qwen3-235B | Tool Selection Accuracy (TSA)69.8 | 8 | 27d ago | |
| GeoScenario 9 Tools 116 (test) | Qwen3-8B | TSA73.8 | 6 | 27d ago |