Causal Variable Identification on MalAlgoQA
84.1F1 (X)GPT-5
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| GPT-5Setting=Decompositional Framework2025.05 | 84.1 | 81.3 | 79.2 | 83.4 | |
| GPT-o4Setting=Decompositional Framework, Model Variant=GPT-o4-mini-high2025.05 | 81.5 | 78.9 | 76.8 | 80.4 | |
| Llama4-MSetting=Decompositional Framework, Model Variant=Llama-4-Maverick-17B-128E2025.05 | 80.6 | 78.2 | 77.8 | 82.4 | |
| Llama4-SSetting=Decompositional Framework, Model Variant=Llama-4-Scout-17B2025.05 | 79.5 | 77.1 | 76.6 | 81.2 | |
| DeepSeekSetting=Decompositional Framework, Model Variant=DeepSeek-VL2025.05 | 75.9 | 73.4 | 63.8 | 72.3 | |
| Gemini2.5Setting=Decompositional Framework, Model Variant=Gemini2.5-Pro2025.05 | 73.5 | 71.2 | 60.2 | 70.5 | |
| Qwen3Setting=Decompositional Framework, Model Variant=Qwen3-VL-235B-A22B Thinking2025.05 | 72.9 | 70.6 | 61.5 | 69.3 |