List your company

Causal Variable Identification on Code-Preference

80.2F1 (X)GPT-o4
48.37656.63864.973.162May 17, 2025

Evaluation results

MethodLinks
GPT-o4Setting=Decompositional Framework, Model Variant=GPT-o4-mini-high2025.0580.26966.377
Llama4-MSetting=Decompositional Framework, Model Variant=Llama-4-Maverick-17B-128E2025.0575.263.465.780.4
Llama4-SSetting=Decompositional Framework, Model Variant=Llama-4-Scout-17B2025.0573.661.964.579.3
Qwen3Setting=Decompositional Framework, Model Variant=Qwen3-VL-235B-A22B Thinking2025.0572.960.550.478.6
Gemini2.5Setting=Decompositional Framework, Model Variant=Gemini2.5-Pro2025.0568.466.548.276.1
DeepSeekSetting=Decompositional Framework, Model Variant=DeepSeek-VL2025.0561.259.352.559.8
GPT-5Setting=Decompositional Framework2025.0549.668.465.975.3