Causal Variable Identification on HumanEval Exe
71.4F1 (X)GPT-o4
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| GPT-o4Setting=Decompositional Framework, Model Variant=GPT-o4-mini-high2025.05 | 71.4 | 69.2 | 66 | 70.3 | |
| GPT-5Setting=Decompositional Framework2025.05 | 69.3 | 66.9 | 63.2 | 67.4 | |
| Llama4-MSetting=Decompositional Framework, Model Variant=Llama-4-Maverick-17B-128E2025.05 | 68.9 | 66.7 | 63 | 67.5 | |
| Llama4-SSetting=Decompositional Framework, Model Variant=Llama-4-Scout-17B2025.05 | 67.8 | 65.7 | 61.9 | 66.3 | |
| Qwen3Setting=Decompositional Framework, Model Variant=Qwen3-VL-235B-A22B Thinking2025.05 | 63.7 | 61.9 | 51.9 | 59.7 | |
| DeepSeekSetting=Decompositional Framework, Model Variant=DeepSeek-VL2025.05 | 62.1 | 59.8 | 53.6 | 60.5 | |
| Gemini2.5Setting=Decompositional Framework, Model Variant=Gemini2.5-Pro2025.05 | 59.6 | 57.3 | 49.7 | 57 |