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

#ModelScore
1GPT-4o72.73
2Qwen 2.5 7B Instruct68.56
3DeepSeek V365.44
4Llama 3 70B Instruct62.72
5InternLM3-8B-Instruct61.44
6GPT-3.561.22
7Mistral 7B Instruct (v0.2)49.75
8Yi-1.5-6B-Chat47.44
9Qwen 2.5 32B Instruct44.28
10Phi-3 Mini 4K Instruct43.63
11Gemini 2.5 Flash41.47

Interactive version: theaggregate.ai/benchmark?slug=terralogic-perception-toolkit · How It Works · Data refreshed daily, snapshot 2026-09-29.