Causal Variable Identification on CVQA Bool
79.8F1 (X)GPT-o4
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| GPT-o4Setting=Decompositional Framework, Model Variant=GPT-o4-mini-high2025.05 | 79.8 | 76.5 | 73.9 | 80.1 | |
| GPT-5Setting=Decompositional Framework2025.05 | 79.4 | 76.2 | 73.5 | 79.3 | |
| Llama4-MSetting=Decompositional Framework, Model Variant=Llama-4-Maverick-17B-128E2025.05 | 79.1 | 76.9 | 72.9 | 79.4 | |
| Llama4-SSetting=Decompositional Framework, Model Variant=Llama-4-Scout-17B2025.05 | 77.9 | 75.8 | 71.8 | 78.3 | |
| Qwen3Setting=Decompositional Framework, Model Variant=Qwen3-VL-235B-A22B Thinking2025.05 | 72.3 | 70.5 | 59.7 | 66.9 | |
| DeepSeekSetting=Decompositional Framework, Model Variant=DeepSeek-VL2025.05 | 70.7 | 68.3 | 60.5 | 68.4 | |
| Gemini2.5Setting=Decompositional Framework, Model Variant=Gemini2.5-Pro2025.05 | 68.5 | 66.9 | 57.3 | 63.2 |