Subcircuit Identification on AMS benchmark Simple (<20 transistors) 1.0
99.7F1 ScoreHeaRT
Evaluation Results
| Method | Links | |
|---|---|---|
| HeaRTLLM Backbone=Claude-4.6-Sonnet, Approach=HeaRT2025.11 | 99.7 | |
| HeaRTLLM Backbone=DeepSeek-V3.2, Approach=HeaRT2025.11 | 99.3 | |
| HeaRTLLM Backbone=GPT-5, Approach=HeaRT2025.11 | 99.3 | |
| HeaRTLLM Backbone=Gemini-2.5 Pro, Approach=HeaRT2025.11 | 97.9 | |
| Few-shot (Text)LLM Backbone=Claude-4.6-Sonnet, Approach=Few-shot (Text), Input=SPICE netlist2025.11 | 76.2 | |
| Few-shot (Image)LLM Backbone=Claude-4.6-Sonnet, Approach=Few-shot (Image), Input=schematic image2025.11 | 75.9 | |
| Few-shot (Text)LLM Backbone=DeepSeek-V3.2, Approach=Few-shot (Text), Input=SPICE netlist2025.11 | 72.9 | |
| Few-shot (Image)LLM Backbone=GPT-5, Approach=Few-shot (Image), Input=schematic image2025.11 | 72.5 | |
| HeaRTLLM Backbone=LLaMA-3.3-70B-Instruct†, Approach=HeaRT2025.11 | 72.4 | |
| Few-shot (Text)LLM Backbone=GPT-5, Approach=Few-shot (Text), Input=SPICE netlist2025.11 | 72.2 | |
| Few-shot (Image)LLM Backbone=DeepSeek-V3.2, Approach=Few-shot (Image), Input=schematic image2025.11 | 71.8 | |
| Few-shot (Text)LLM Backbone=Gemini-2.5 Pro, Approach=Few-shot (Text), Input=SPICE netlist2025.11 | 69.7 | |
| Few-shot (Image)LLM Backbone=Gemini-2.5 Pro, Approach=Few-shot (Image), Input=schematic image2025.11 | 68.1 | |
| Few-shot (Text)LLM Backbone=LLaMA-3.3-70B-Instruct†, Approach=Few-shot (Text), Input=SPICE netlist2025.11 | 57.1 |