ResearchTasksAgent tool-use planningAgent tool-use planningFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedThinkGeo 14 Tools (test)Qwen3-235B77.7Tool Selection Accuracy (TSA)8May 7, 2026EarthBench 104 Tools (test)Qwen3-235B69.8Tool Selection Accuracy (TSA)8May 7, 2026GeoScenario 9 Tools 116 (test)Qwen3-8B73.8TSA6May 7, 2026