Causal Variable Identification on CLOMO
89.8F1 (X)GPT-5
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| GPT-5Setting=Decompositional Framework2025.05 | 89.8 | 87.6 | 83.1 | 89.4 | |
| Llama4-MSetting=Decompositional Framework, Model Variant=Llama-4-Maverick-17B-128E2025.05 | 88.8 | 87 | 78.6 | 86 | |
| GPT-o4Setting=Decompositional Framework, Model Variant=GPT-o4-mini-high2025.05 | 88.1 | 85.6 | 81.3 | 87.9 | |
| Llama4-SSetting=Decompositional Framework, Model Variant=Llama-4-Scout-17B2025.05 | 87.1 | 85.3 | 77.2 | 84.9 | |
| DeepSeekSetting=Decompositional Framework, Model Variant=DeepSeek-VL2025.05 | 86.4 | 84.2 | 73.5 | 80.7 | |
| Gemini2.5Setting=Decompositional Framework, Model Variant=Gemini2.5-Pro2025.05 | 84.3 | 82.8 | 71.2 | 78.9 | |
| Qwen3Setting=Decompositional Framework, Model Variant=Qwen3-VL-235B-A22B Thinking2025.05 | 83.5 | 81.9 | 68.9 | 77.4 |