Causal Variable Identification on CVQA Count
74.7F1 (X)GPT-5
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| GPT-5Setting=Decompositional Framework2025.05 | 74.7 | 72.3 | 69.6 | 75.2 | |
| Llama4-MSetting=Decompositional Framework, Model Variant=Llama-4-Maverick-17B-128E2025.05 | 74.4 | 72.5 | 70.2 | 75.9 | |
| GPT-o4Setting=Decompositional Framework, Model Variant=GPT-o4-mini-high2025.05 | 74.3 | 72.9 | 70.1 | 76.2 | |
| Llama4-SSetting=Decompositional Framework, Model Variant=Llama-4-Scout-17B2025.05 | 73.6 | 71.9 | 68.9 | 74.8 | |
| Qwen3Setting=Decompositional Framework, Model Variant=Qwen3-VL-235B-A22B Thinking2025.05 | 68.9 | 67.2 | 56.8 | 63.6 | |
| DeepSeekSetting=Decompositional Framework, Model Variant=DeepSeek-VL2025.05 | 67.4 | 65.1 | 57.9 | 65.1 | |
| Gemini2.5Setting=Decompositional Framework, Model Variant=Gemini2.5-Pro2025.05 | 65.8 | 63.7 | 54.7 | 60.4 |