TerraLogic - Tool Selection: leaderboard
Metric: Tool-selection accuracy (ToolAcc) (%) in the step-by-step setting over the 545 TerraLogic optical, SAR and infrared 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 February 2027. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 2.5 7B Instruct | 74.71 |
| 2 | GPT-4o | 72.01 |
| 3 | Llama 3 70B Instruct | 67.47 |
| 4 | DeepSeek V3 | 66.33 |
| 5 | Qwen 2.5 32B Instruct | 58 |
| 6 | InternLM3-8B-Instruct | 57.72 |
| 7 | GPT-3.5 | 57.12 |
| 8 | Mistral 7B Instruct (v0.2) | 47.05 |
| 9 | Gemini 2.5 Flash | 43.31 |
| 10 | Yi-1.5-6B-Chat | 42.08 |
| 11 | Phi-3 Mini 4K Instruct | 41.14 |
Interactive version: theaggregate.ai/benchmark?slug=terralogic-tool-selection · How It Works · Data refreshed daily, snapshot 2026-09-29.