Political Position Ranking on Political Judgements P Full Distribution 1.0
0d_footruleWorst-case Baseline
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Worst-case Baselinetype=Baseline2026.02 | 0 | 0 | -1 | 0 | |
| Random Baselinetype=Baseline2026.02 | 0.333 | 0.5 | 0 | 50 | |
| Gemini 1.5 ProModel=Gemini 1.5 Pro2026.02 | 0.612 | 0.734 | 0.655 | 61 | |
| Qwen QwQModel=Qwen QwQ2026.02 | 0.661 | 0.77 | 0.747 | 62.1 | |
| GPT 4o MiniModel=GPT 4o Mini2026.02 | 0.661 | 0.767 | 0.73 | 64.5 | |
| Claude 3.5 HaikuModel=Claude 3.5 Haiku2026.02 | 0.679 | 0.772 | 0.734 | 64 | |
| o3 MiniModel=o3 Mini2026.02 | 0.684 | 0.779 | 0.766 | 64.4 | |
| DeepSeek-R1Model=DeepSeek-R12026.02 | 0.691 | 0.781 | 0.753 | 59.5 | |
| GPT 4.5Model=GPT 4.52026.02 | 0.696 | 0.793 | 0.783 | 63 | |
| DeepSeek-V3Model=DeepSeek-V32026.02 | 0.698 | 0.777 | 0.739 | 59.5 | |
| Ensemble 2Aggregation=Ensemble2026.02 | 0.721 | 0.804 | 0.803 | 62.2 | |
| Ensemble 1Aggregation=Ensemble2026.02 | 0.726 | 0.81 | 0.808 | 60.3 | |
| Ensemble 3Aggregation=Ensemble2026.02 | 0.728 | 0.806 | 0.799 | 58.3 | |
| Human (right)type=Individual Human2026.02 | 0.886 | 0.922 | 0.966 | 79 | |
| Human (left)type=Individual Human2026.02 | 0.904 | 0.934 | 0.974 | 82.7 | |
| Human (agg)type=Human aggregate2026.02 | 1 | 1 | 1 | 100 |