Feedback Loop Identification on AMS benchmark Medium (20–40 transistors) 1.0
96.2F1 ScoreHeaRT
Evaluation Results
| Method | Links | |
|---|---|---|
| HeaRTLLM Backbone=Claude-4.6-Sonnet, Approach=HeaRT2025.11 | 96.2 | |
| HeaRTLLM Backbone=GPT-5, Approach=HeaRT2025.11 | 93.1 | |
| HeaRTLLM Backbone=DeepSeek-V3.2, Approach=HeaRT2025.11 | 91.7 | |
| HeaRTLLM Backbone=Gemini-2.5 Pro, Approach=HeaRT2025.11 | 89.1 | |
| Few-shot (Image)LLM Backbone=Claude-4.6-Sonnet, Approach=Few-shot (Image)2025.11 | 69.8 | |
| Few-shot (Text)LLM Backbone=Claude-4.6-Sonnet, Approach=Few-shot (Text)2025.11 | 67.5 | |
| Few-shot (Image)LLM Backbone=GPT-5, Approach=Few-shot (Image)2025.11 | 65.9 | |
| Few-shot (Text)LLM Backbone=GPT-5, Approach=Few-shot (Text)2025.11 | 63.8 | |
| Few-shot (Image)LLM Backbone=DeepSeek-V3.2, Approach=Few-shot (Image)2025.11 | 62.6 | |
| Few-shot (Text)LLM Backbone=DeepSeek-V3.2, Approach=Few-shot (Text)2025.11 | 62.1 | |
| Few-shot (Image)LLM Backbone=Gemini-2.5 Pro, Approach=Few-shot (Image)2025.11 | 55.4 | |
| Few-shot (Text)LLM Backbone=Gemini-2.5 Pro, Approach=Few-shot (Text)2025.11 | 47.1 | |
| HeaRTLLM Backbone=LLaMA-3.3-70B-Instruct†, Approach=HeaRT2025.11 | 36.2 | |
| Few-shot (Text)LLM Backbone=LLaMA-3.3-70B-Instruct†, Approach=Few-shot (Text)2025.11 | 15.3 |