TerraLogic - Spatial Statistics Toolkit: leaderboard
Metric: End-to-end score (%) of tool-augmented predictions on the Spatial Statistics toolkit over the 545 TerraLogic remote-sensing tasks, each model driving the HieraPlan tool agent under a ReAct-style protocol in OpenCompass; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o | 88.38 |
| 2 | Qwen 2.5 7B Instruct | 73.03 |
| 3 | Llama 3 70B Instruct | 71.62 |
| 4 | Qwen 2.5 32B Instruct | 67.4 |
| 5 | DeepSeek V3 | 66.04 |
| 6 | GPT-3.5 | 61.04 |
| 7 | InternLM3-8B-Instruct | 53.7 |
| 8 | Mistral 7B Instruct (v0.2) | 44.05 |
| 9 | Gemini 2.5 Flash | 40.89 |
| 10 | Yi-1.5-6B-Chat | 38.73 |
| 11 | Phi-3 Mini 4K Instruct | 7.52 |
Interactive version: theaggregate.ai/benchmark?slug=terralogic-spatial-statistics-toolkit · How It Works · Data refreshed daily, snapshot 2026-09-29.