TerraLogic: leaderboard
Metric: Final answer accuracy (%, AnsAcc) over the 545 TerraLogic optical, SAR and infrared remote-sensing tasks, judged by GPT-4o-mini with a rubric against the ground-truth answer and its key arguments; each model drives the HieraPlan tool agent under a ReAct-style protocol in OpenCompass; higher is better. Source: arxiv.org. Saturation forecast: Around 2031. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o | 25.7 |
| 2 | GPT-3.5 | 24.4 |
| 3 | Llama 3 70B Instruct | 22.75 |
| 4 | Qwen 2.5 7B Instruct | 22.57 |
| 5 | DeepSeek V3 | 21.28 |
| 6 | Qwen 2.5 32B Instruct | 19.08 |
| 7 | InternLM3-8B-Instruct | 18.9 |
| 8 | Mistral 7B Instruct (v0.2) | 13.21 |
| 9 | Gemini 2.5 Flash | 12.04 |
| 10 | Yi-1.5-6B-Chat | 10.83 |
| 11 | Phi-3 Mini 4K Instruct | 3.67 |
Interactive version: theaggregate.ai/benchmark?slug=terralogic · How It Works · Data refreshed daily, snapshot 2026-09-29.