TerraLogic - Perception Toolkit: leaderboard
Metric: End-to-end score (%) of tool-augmented predictions on the Perception 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 2029. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o | 72.73 |
| 2 | Qwen 2.5 7B Instruct | 68.56 |
| 3 | DeepSeek V3 | 65.44 |
| 4 | Llama 3 70B Instruct | 62.72 |
| 5 | InternLM3-8B-Instruct | 61.44 |
| 6 | GPT-3.5 | 61.22 |
| 7 | Mistral 7B Instruct (v0.2) | 49.75 |
| 8 | Yi-1.5-6B-Chat | 47.44 |
| 9 | Qwen 2.5 32B Instruct | 44.28 |
| 10 | Phi-3 Mini 4K Instruct | 43.63 |
| 11 | Gemini 2.5 Flash | 41.47 |
Interactive version: theaggregate.ai/benchmark?slug=terralogic-perception-toolkit · How It Works · Data refreshed daily, snapshot 2026-09-29.