TerraLogic - Spatial Relations Toolkit: leaderboard
Metric: End-to-end score (%) of tool-augmented predictions on the Spatial Relations 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: Around June 2027. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 2.5 7B Instruct | 82.42 |
| 2 | GPT-4o | 77.95 |
| 3 | Llama 3 70B Instruct | 62.54 |
| 4 | Qwen 2.5 32B Instruct | 61.47 |
| 5 | InternLM3-8B-Instruct | 60.7 |
| 6 | DeepSeek V3 | 57.93 |
| 7 | GPT-3.5 | 53.3 |
| 8 | Phi-3 Mini 4K Instruct | 51.74 |
| 9 | Mistral 7B Instruct (v0.2) | 45.23 |
| 10 | Gemini 2.5 Flash | 41.51 |
| 11 | Yi-1.5-6B-Chat | 36.02 |
Interactive version: theaggregate.ai/benchmark?slug=terralogic-spatial-relations-toolkit · How It Works · Data refreshed daily, snapshot 2026-09-29.