Causal Variable Identification on RNN-Topo
87.9F1 (X)GPT-5
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| GPT-5Setting=Decompositional Framework2025.05 | 87.9 | 85.4 | 81.7 | 86.3 | |
| GPT-o4Setting=Decompositional Framework, Model Variant=GPT-o4-mini-high2025.05 | 85.9 | 83.7 | 79.4 | 85.6 | |
| Llama4-MSetting=Decompositional Framework, Model Variant=Llama-4-Maverick-17B-128E2025.05 | 85.7 | 84.2 | 76.6 | 84.4 | |
| Llama4-SSetting=Decompositional Framework, Model Variant=Llama-4-Scout-17B2025.05 | 84.3 | 82.6 | 75.3 | 83.1 | |
| DeepSeekSetting=Decompositional Framework, Model Variant=DeepSeek-VL2025.05 | 83.8 | 82 | 71.5 | 78.9 | |
| Gemini2.5Setting=Decompositional Framework, Model Variant=Gemini2.5-Pro2025.05 | 81.7 | 80.1 | 69.3 | 76.4 | |
| Qwen3Setting=Decompositional Framework, Model Variant=Qwen3-VL-235B-A22B Thinking2025.05 | 80.4 | 78.6 | 67.1 | 75.8 |