List your company

Political Position Ranking on Political Judgements P Full Distribution 1.0

0d_footruleWorst-case Baseline
-0.040.230.50.77Feb 20, 2026

Evaluation results

MethodLinks
Worst-case Baselinetype=Baseline2026.0200-10
Random Baselinetype=Baseline2026.020.3330.5050
Gemini 1.5 ProModel=Gemini 1.5 Pro2026.020.6120.7340.65561
Qwen QwQModel=Qwen QwQ2026.020.6610.770.74762.1
GPT 4o MiniModel=GPT 4o Mini2026.020.6610.7670.7364.5
Claude 3.5 HaikuModel=Claude 3.5 Haiku2026.020.6790.7720.73464
o3 MiniModel=o3 Mini2026.020.6840.7790.76664.4
DeepSeek-R1Model=DeepSeek-R12026.020.6910.7810.75359.5
GPT 4.5Model=GPT 4.52026.020.6960.7930.78363
DeepSeek-V3Model=DeepSeek-V32026.020.6980.7770.73959.5
Ensemble 2Aggregation=Ensemble2026.020.7210.8040.80362.2
Ensemble 1Aggregation=Ensemble2026.020.7260.810.80860.3
Ensemble 3Aggregation=Ensemble2026.020.7280.8060.79958.3
Human (right)type=Individual Human2026.020.8860.9220.96679
Human (left)type=Individual Human2026.020.9040.9340.97482.7
Human (agg)type=Human aggregate2026.02111100